ASRock B450M Pro4 R2.0 - FreeBSD

root@locaal:~ # nvidia-smi
Sun May  3 12:08:23 2026       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 595.58.03              Driver Version: 595.58.03      CUDA Version: N/A      |
+-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA GeForce RTX 3060        Off |   00000000:06:00.0 Off |                  N/A |
|  0%   47C    P8             17W /  170W |       1MiB /  12288MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

root@locaal:~ # freebsd-version -ku
13.5-RELEASE-p13
13.5-RELEASE-p14

root@locaal:~ # uname -a
FreeBSD locaal 13.5-RELEASE-p13 FreeBSD 13.5-RELEASE-p13 GENERIC amd64

root@locaal:~ # freebsd-update fetch
src component not installed, skipped
[..]
The following files will be updated as part of updating to
13.5-RELEASE-p14:
/bin/freebsd-version
/boot/kernel/kernel
/boot/kernel/pf.ko
/lib/libnv.so.0
[..]
/sbin/dhclient
/usr/lib/libnv.a
/usr/lib/libnv_p.a
/usr/lib32/libnv.a
/usr/lib32/libnv.so.0
/usr/lib32/libnv_p.a
/usr/share/zoneinfo/America/Ensenada
/usr/share/zoneinfo/America/Santa_Isabel
/usr/share/zoneinfo/America/Tijuana
/usr/share/zoneinfo/America/Vancouver
/usr/share/zoneinfo/Canada/Pacific
/usr/share/zoneinfo/Europe/Chisinau
/usr/share/zoneinfo/Europe/Tiraspol
/usr/share/zoneinfo/Mexico/BajaNorte
/usr/share/zoneinfo/zone.tab
/usr/share/zoneinfo/zone1970.tab

root@locaal:~ # freebsd-update install
src component not installed, skipped
Installing updates...
Restarting sshd after upgrade
Performing sanity check on sshd configuration.
Stopping sshd.
Waiting for PIDS: 1138.
Performing sanity check on sshd configuration.
Starting sshd.
Scanning //usr/share/certs/blacklisted for certificates...
Scanning //usr/share/certs/trusted for certificates...
 done.

May  3 11:54:51 locaal pkg[28463]: lcms2 upgraded: 2.18 -> 2.19 
May  3 11:54:51 locaal pkg[28463]: libXpm upgraded: 3.5.17_1 -> 3.5.19 
May  3 11:54:51 locaal pkg[28463]: libnghttp2 upgraded: 1.68.0 -> 1.68.1 
May  3 11:54:52 locaal pkg[28463]: curl upgraded: 8.19.0_1 -> 8.19.0_2 
May  3 11:54:53 locaal pkg[28463]: nss upgraded: 3.123 -> 3.123.1 
May  3 11:54:56 locaal pkg[28463]: nvidia-driver upgraded: 595.58.03 -> 595.58.03_2 
May  3 11:54:56 locaal pkg[28463]: py311-requests upgraded: 2.32.5 -> 2.33.1 
May  3 11:54:57 locaal pkg[28463]: py311-tzdata upgraded: 2026.1 -> 2026.2 
May  3 11:54:58 locaal pkg[28463]: uriparser upgraded: 1.0.0_1 -> 1.0.1 

root@locaal:~ # freebsd-version -ku
13.5-RELEASE-p12
13.5-RELEASE-p12

root@locaal:~ # uname -a
FreeBSD locaal 13.5-RELEASE-p12 FreeBSD 13.5-RELEASE-p12 GENERIC amd64

root@locaal:~ # freebsd-update fetch
src component not installed, skipped
[..]
The following files will be updated as part of updating to
13.5-RELEASE-p12:
/bin/freebsd-version
/boot/kernel/aout.ko
/boot/kernel/fasttrap.ko
/boot/kernel/hwpmc.ko
/boot/kernel/kernel
/boot/kernel/linprocfs.ko
/boot/kernel/linux.ko
/boot/kernel/linux64.ko
/boot/kernel/linux_common.ko
/boot/kernel/mem.ko
/boot/kernel/procfs.ko
/boot/kernel/sgx.ko
/boot/kernel/sysvshm.ko
/boot/kernel/tmpfs.ko
/boot/kernel/vmm.ko
/usr/include/vm/vm_map.h
/usr/share/man/man3/pkru.3.gz

root@locaal:~ # freebsd-update install
src component not installed, skipped
Installing updates...
Restarting sshd after upgrade
Performing sanity check on sshd configuration.
Stopping sshd.
Waiting for PIDS: 1135.
Performing sanity check on sshd configuration.
Starting sshd.
Scanning //usr/share/certs/blacklisted for certificates...
Scanning //usr/share/certs/trusted for certificates...
 done.

Apr 21 21:27:37 locaal pkg[22916]: libXdamage reinstalled: 1.1.6 -> 1.1.6 
Apr 21 21:27:37 locaal pkg[22916]: libXfont2 reinstalled: 2.0.6 -> 2.0.6 
Apr 21 21:27:37 locaal pkg[22916]: libXrandr reinstalled: 1.5.4 -> 1.5.4 
Apr 21 21:27:37 locaal pkg[22916]: libXxf86vm reinstalled: 1.1.6 -> 1.1.6 
Apr 21 21:27:37 locaal pkg[22916]: libepoxy reinstalled: 1.5.10 -> 1.5.10 
Apr 21 21:27:37 locaal pkg[22916]: nss upgraded: 3.122 -> 3.123 
Apr 21 21:27:38 locaal pkg[22916]: slurm-wlm upgraded: 25.11.4 -> 25.11.5 
Apr 21 21:27:39 locaal pkg[22916]: xorg-server upgraded: 21.1.20,1 -> 21.1.22,1 

Apr 19 17:28:17 locaal pkg[17862]: aom upgraded: 3.13.2 -> 3.13.3 
Apr 19 17:28:17 locaal pkg[17862]: jpeg-turbo upgraded: 3.1.3 -> 3.1.4.1 
Apr 19 17:28:17 locaal pkg[17862]: openexr upgraded: 3.4.8 -> 3.4.9 
Apr 19 17:28:17 locaal pkg[17862]: png upgraded: 1.6.55 -> 1.6.57 
Apr 19 17:28:18 locaal pkg[17862]: graphviz upgraded: 14.1.4 -> 14.1.4_1 
Apr 19 17:28:33 locaal pkg[17862]: python311 upgraded: 3.11.15_1 -> 3.11.15_2 
Apr 19 17:28:34 locaal pkg[17862]: py311-lxml upgraded: 6.0.2 -> 6.0.4 
Apr 19 17:28:35 locaal pkg[17862]: tiff upgraded: 4.7.1 -> 4.7.1_1 
Apr 19 17:28:35 locaal pkg[17862]: wolfssl upgraded: 5.9.0 -> 5.9.0_1 

tingo@locaal:~/work/ai $ llama-server --models-preset /home/tingo/work/ai/models/config.ini --host 0.0.0.0 --port 9011 --device Vulkan0 -ngl 15
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA GeForce RTX 3060 (NVIDIA) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2
main: n_parallel is set to auto, using n_parallel = 4 and kv_unified = true
build: 8182 (unknown) with Clang 19.1.7 for FreeBSD amd64
system info: n_threads = 6, n_threads_batch = 6, total_threads = 12

system_info: n_threads = 6 (n_threads_batch = 6) / 12 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | OPENMP = 1 | REPACK = 1 | 

init: using 11 threads for HTTP server
failed to get server executable path: failed to resolve /proc/self/exe
using original argv[0] as fallback: llama-server
srv   load_models: Loaded 0 cached model presets
srv   load_models: Loaded 1 custom model presets from /home/tingo/work/ai/models/config.ini
srv   load_models: Available models (1) (*: custom preset)
srv   load_models:   * Gemma4-31B-IT
main: starting router server, no model will be loaded in this process
start: binding port with default address family
main: router server is listening on http://0.0.0.0:9011
main: NOTE: router mode is experimental
main:       it is not recommended to use this mode in untrusted environments

srv  log_server_r: done request: GET / 10.1.150.52 200
srv          load: spawning server instance with name=Gemma4-31B-IT on port 26263
srv          load: spawning server instance with args:
srv          load:   llama-server
srv          load:   --chat-template-file
srv          load:   /home/tingo/work/ai/models/Gemma4-31B-IT/chat_template.jinja
srv          load:   --host
srv          load:   127.0.0.1
srv          load:   --port
srv          load:   26263
srv          load:   --alias
srv          load:   Gemma4-31B-IT
srv          load:   --device
srv          load:   Vulkan0
srv          load:   --model
srv          load:   /home/tingo/work/ai/models/Gemma4-31B-IT/gemma-4-31B-it-Q4_K_M.gguf
srv          load:   --mmproj
srv          load:   /home/tingo/work/ai/models/Gemma4-31B-IT/mmproj-gemma-4-31B-it-BF16.gguf
srv          load:   --n-gpu-layers
srv          load:   15
srv    operator(): got exception: {"error":{"code":500,"message":"failed to spawn server instance","type":"server_error"}}
srv  log_server_r: done request: POST /models/load 10.1.150.52 500
srv  ensure_model: model name=Gemma4-31B-IT is not loaded, loading...
srv          load: spawning server instance with name=Gemma4-31B-IT on port 52349
srv          load: spawning server instance with args:
srv          load:   llama-server
srv          load:   --chat-template-file
srv          load:   /home/tingo/work/ai/models/Gemma4-31B-IT/chat_template.jinja
srv          load:   --host
srv          load:   127.0.0.1
srv          load:   --port
srv          load:   52349
srv          load:   --alias
srv          load:   Gemma4-31B-IT
srv          load:   --device
srv          load:   Vulkan0
srv          load:   --model
srv          load:   /home/tingo/work/ai/models/Gemma4-31B-IT/gemma-4-31B-it-Q4_K_M.gguf
srv          load:   --mmproj
srv          load:   /home/tingo/work/ai/models/Gemma4-31B-IT/mmproj-gemma-4-31B-it-BF16.gguf
srv          load:   --n-gpu-layers
srv          load:   15
srv    operator(): got exception: {"error":{"code":500,"message":"failed to spawn server instance","type":"server_error"}}
srv  log_server_r: done request: POST /v1/chat/completions 10.1.150.52 500

tingo@locaal:~ $ llama-server --list-devices
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA GeForce RTX 3060 (NVIDIA) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2
Available devices:
  Vulkan0: NVIDIA GeForce RTX 3060 (12534 MiB, 12393 MiB free)

tingo@locaal:~ $ llama-server --help
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA GeForce RTX 3060 (NVIDIA) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2
----- common params -----

-h,    --help, --usage                  print usage and exit
--version                               show version and build info
--license                               show source code license and dependencies
-cl,   --cache-list                     show list of models in cache
--completion-bash                       print source-able bash completion script for llama.cpp
--verbose-prompt                        print a verbose prompt before generation (default: false)
-t,    --threads N                      number of CPU threads to use during generation (default: -1)
                                        (env: LLAMA_ARG_THREADS)
-tb,   --threads-batch N                number of threads to use during batch and prompt processing (default:
                                        same as --threads)
-C,    --cpu-mask M                     CPU affinity mask: arbitrarily long hex. Complements cpu-range
                                        (default: "")
-Cr,   --cpu-range lo-hi                range of CPUs for affinity. Complements --cpu-mask
--cpu-strict <0|1>                      use strict CPU placement (default: 0)
--prio N                                set process/thread priority : low(-1), normal(0), medium(1), high(2),
                                        realtime(3) (default: 0)
--poll <0...100>                        use polling level to wait for work (0 - no polling, default: 50)
-Cb,   --cpu-mask-batch M               CPU affinity mask: arbitrarily long hex. Complements cpu-range-batch
                                        (default: same as --cpu-mask)
-Crb,  --cpu-range-batch lo-hi          ranges of CPUs for affinity. Complements --cpu-mask-batch
--cpu-strict-batch <0|1>                use strict CPU placement (default: same as --cpu-strict)
--prio-batch N                          set process/thread priority : 0-normal, 1-medium, 2-high, 3-realtime
                                        (default: 0)
--poll-batch <0|1>                      use polling to wait for work (default: same as --poll)
-c,    --ctx-size N                     size of the prompt context (default: 0, 0 = loaded from model)
                                        (env: LLAMA_ARG_CTX_SIZE)
-n,    --predict, --n-predict N         number of tokens to predict (default: -1, -1 = infinity)
                                        (env: LLAMA_ARG_N_PREDICT)
-b,    --batch-size N                   logical maximum batch size (default: 2048)
                                        (env: LLAMA_ARG_BATCH)
-ub,   --ubatch-size N                  physical maximum batch size (default: 512)
                                        (env: LLAMA_ARG_UBATCH)
--keep N                                number of tokens to keep from the initial prompt (default: 0, -1 =
                                        all)
--swa-full                              use full-size SWA cache (default: false)
                                        [(more
                                        info)](https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
                                        (env: LLAMA_ARG_SWA_FULL)
-fa,   --flash-attn [on|off|auto]       set Flash Attention use ('on', 'off', or 'auto', default: 'auto')
                                        (env: LLAMA_ARG_FLASH_ATTN)
--perf, --no-perf                       whether to enable internal libllama performance timings (default:
                                        false)
                                        (env: LLAMA_ARG_PERF)
-e,    --escape, --no-escape            whether to process escapes sequences (\n, \r, \t, \', \", \\)
                                        (default: true)
--rope-scaling {none,linear,yarn}       RoPE frequency scaling method, defaults to linear unless specified by
                                        the model
                                        (env: LLAMA_ARG_ROPE_SCALING_TYPE)
--rope-scale N                          RoPE context scaling factor, expands context by a factor of N
                                        (env: LLAMA_ARG_ROPE_SCALE)
--rope-freq-base N                      RoPE base frequency, used by NTK-aware scaling (default: loaded from
                                        model)
                                        (env: LLAMA_ARG_ROPE_FREQ_BASE)
--rope-freq-scale N                     RoPE frequency scaling factor, expands context by a factor of 1/N
                                        (env: LLAMA_ARG_ROPE_FREQ_SCALE)
--yarn-orig-ctx N                       YaRN: original context size of model (default: 0 = model training
                                        context size)
                                        (env: LLAMA_ARG_YARN_ORIG_CTX)
--yarn-ext-factor N                     YaRN: extrapolation mix factor (default: -1.00, 0.0 = full
                                        interpolation)
                                        (env: LLAMA_ARG_YARN_EXT_FACTOR)
--yarn-attn-factor N                    YaRN: scale sqrt(t) or attention magnitude (default: -1.00)
                                        (env: LLAMA_ARG_YARN_ATTN_FACTOR)
--yarn-beta-slow N                      YaRN: high correction dim or alpha (default: -1.00)
                                        (env: LLAMA_ARG_YARN_BETA_SLOW)
--yarn-beta-fast N                      YaRN: low correction dim or beta (default: -1.00)
                                        (env: LLAMA_ARG_YARN_BETA_FAST)
-kvo,  --kv-offload, -nkvo, --no-kv-offload
                                        whether to enable KV cache offloading (default: enabled)
                                        (env: LLAMA_ARG_KV_OFFLOAD)
--repack, -nr, --no-repack              whether to enable weight repacking (default: enabled)
                                        (env: LLAMA_ARG_REPACK)
--no-host                               bypass host buffer allowing extra buffers to be used
                                        (env: LLAMA_ARG_NO_HOST)
-ctk,  --cache-type-k TYPE              KV cache data type for K
                                        allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1
                                        (default: f16)
                                        (env: LLAMA_ARG_CACHE_TYPE_K)
-ctv,  --cache-type-v TYPE              KV cache data type for V
                                        allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1
                                        (default: f16)
                                        (env: LLAMA_ARG_CACHE_TYPE_V)
-dt,   --defrag-thold N                 KV cache defragmentation threshold (DEPRECATED)
                                        (env: LLAMA_ARG_DEFRAG_THOLD)
--mlock                                 force system to keep model in RAM rather than swapping or compressing
                                        (env: LLAMA_ARG_MLOCK)
--mmap, --no-mmap                       whether to memory-map model. (if mmap disabled, slower load but may
                                        reduce pageouts if not using mlock) (default: enabled)
                                        (env: LLAMA_ARG_MMAP)
-dio,  --direct-io, -ndio, --no-direct-io
                                        use DirectIO if available. (default: disabled)
                                        (env: LLAMA_ARG_DIO)
--numa TYPE                             attempt optimizations that help on some NUMA systems
                                        - distribute: spread execution evenly over all nodes
                                        - isolate: only spawn threads on CPUs on the node that execution
                                        started on
                                        - numactl: use the CPU map provided by numactl
                                        if run without this previously, it is recommended to drop the system
                                        page cache before using this
                                        see https://github.com/ggml-org/llama.cpp/issues/1437
                                        (env: LLAMA_ARG_NUMA)
-dev,  --device <dev1,dev2,..>          comma-separated list of devices to use for offloading (none = don't
                                        offload)
                                        use --list-devices to see a list of available devices
                                        (env: LLAMA_ARG_DEVICE)
--list-devices                          print list of available devices and exit
-ot,   --override-tensor <tensor name pattern>=<buffer type>,...
                                        override tensor buffer type
                                        (env: LLAMA_ARG_OVERRIDE_TENSOR)
-cmoe, --cpu-moe                        keep all Mixture of Experts (MoE) weights in the CPU
                                        (env: LLAMA_ARG_CPU_MOE)
-ncmoe, --n-cpu-moe N                   keep the Mixture of Experts (MoE) weights of the first N layers in the
                                        CPU
                                        (env: LLAMA_ARG_N_CPU_MOE)
-ngl,  --gpu-layers, --n-gpu-layers N   max. number of layers to store in VRAM, either an exact number,
                                        'auto', or 'all' (default: auto)
                                        (env: LLAMA_ARG_N_GPU_LAYERS)
-sm,   --split-mode {none,layer,row}    how to split the model across multiple GPUs, one of:
                                        - none: use one GPU only
                                        - layer (default): split layers and KV across GPUs
                                        - row: split rows across GPUs
                                        (env: LLAMA_ARG_SPLIT_MODE)
-ts,   --tensor-split N0,N1,N2,...      fraction of the model to offload to each GPU, comma-separated list of
                                        proportions, e.g. 3,1
                                        (env: LLAMA_ARG_TENSOR_SPLIT)
-mg,   --main-gpu INDEX                 the GPU to use for the model (with split-mode = none), or for
                                        intermediate results and KV (with split-mode = row) (default: 0)
                                        (env: LLAMA_ARG_MAIN_GPU)
-fit,  --fit [on|off]                   whether to adjust unset arguments to fit in device memory ('on' or
                                        'off', default: 'on')
                                        (env: LLAMA_ARG_FIT)
-fitt, --fit-target MiB0,MiB1,MiB2,...
                                        target margin per device for --fit, comma-separated list of values,
                                        single value is broadcast across all devices, default: 1024
                                        (env: LLAMA_ARG_FIT_TARGET)
-fitc, --fit-ctx N                      minimum ctx size that can be set by --fit option, default: 4096
                                        (env: LLAMA_ARG_FIT_CTX)
--check-tensors                         check model tensor data for invalid values (default: false)
--override-kv KEY=TYPE:VALUE,...        advanced option to override model metadata by key. to specify multiple
                                        overrides, either use comma-separated values.
                                        types: int, float, bool, str. example: --override-kv
                                        tokenizer.ggml.add_bos_token=bool:false,tokenizer.ggml.add_eos_token=bool:false
--op-offload, --no-op-offload           whether to offload host tensor operations to device (default: true)
--lora FNAME                            path to LoRA adapter (use comma-separated values to load multiple
                                        adapters)
--lora-scaled FNAME:SCALE,...           path to LoRA adapter with user defined scaling (format:
                                        FNAME:SCALE,...)
                                        note: use comma-separated values
--control-vector FNAME                  add a control vector
                                        note: use comma-separated values to add multiple control vectors
--control-vector-scaled FNAME:SCALE,...
                                        add a control vector with user defined scaling SCALE
                                        note: use comma-separated values (format: FNAME:SCALE,...)
--control-vector-layer-range START END
                                        layer range to apply the control vector(s) to, start and end inclusive
-m,    --model FNAME                    model path to load
                                        (env: LLAMA_ARG_MODEL)
-mu,   --model-url MODEL_URL            model download url (default: unused)
                                        (env: LLAMA_ARG_MODEL_URL)
-dr,   --docker-repo [<repo>/]<model>[:quant]
                                        Docker Hub model repository. repo is optional, default to ai/. quant
                                        is optional, default to :latest.
                                        example: gemma3
                                        (default: unused)
                                        (env: LLAMA_ARG_DOCKER_REPO)
-hf,   -hfr, --hf-repo <user>/<model>[:quant]
                                        Hugging Face model repository; quant is optional, case-insensitive,
                                        default to Q4_K_M, or falls back to the first file in the repo if
                                        Q4_K_M doesn't exist.
                                        mmproj is also downloaded automatically if available. to disable, add
                                        --no-mmproj
                                        example: unsloth/phi-4-GGUF:q4_k_m
                                        (default: unused)
                                        (env: LLAMA_ARG_HF_REPO)
-hfd,  -hfrd, --hf-repo-draft <user>/<model>[:quant]
                                        Same as --hf-repo, but for the draft model (default: unused)
                                        (env: LLAMA_ARG_HFD_REPO)
-hff,  --hf-file FILE                   Hugging Face model file. If specified, it will override the quant in
                                        --hf-repo (default: unused)
                                        (env: LLAMA_ARG_HF_FILE)
-hfv,  -hfrv, --hf-repo-v <user>/<model>[:quant]
                                        Hugging Face model repository for the vocoder model (default: unused)
                                        (env: LLAMA_ARG_HF_REPO_V)
-hffv, --hf-file-v FILE                 Hugging Face model file for the vocoder model (default: unused)
                                        (env: LLAMA_ARG_HF_FILE_V)
-hft,  --hf-token TOKEN                 Hugging Face access token (default: value from HF_TOKEN environment
                                        variable)
                                        (env: HF_TOKEN)
--log-disable                           Log disable
--log-file FNAME                        Log to file
                                        (env: LLAMA_LOG_FILE)
--log-colors [on|off|auto]              Set colored logging ('on', 'off', or 'auto', default: 'auto')
                                        'auto' enables colors when output is to a terminal
                                        (env: LLAMA_LOG_COLORS)
-v,    --verbose, --log-verbose         Set verbosity level to infinity (i.e. log all messages, useful for
                                        debugging)
--offline                               Offline mode: forces use of cache, prevents network access
                                        (env: LLAMA_OFFLINE)
-lv,   --verbosity, --log-verbosity N   Set the verbosity threshold. Messages with a higher verbosity will be
                                        ignored. Values:
                                         - 0: generic output
                                         - 1: error
                                         - 2: warning
                                         - 3: info
                                         - 4: debug
                                        (default: 3)

                                        (env: LLAMA_LOG_VERBOSITY)
--log-prefix                            Enable prefix in log messages
                                        (env: LLAMA_LOG_PREFIX)
--log-timestamps                        Enable timestamps in log messages
                                        (env: LLAMA_LOG_TIMESTAMPS)
-ctkd, --cache-type-k-draft TYPE        KV cache data type for K for the draft model
                                        allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1
                                        (default: f16)
                                        (env: LLAMA_ARG_CACHE_TYPE_K_DRAFT)
-ctvd, --cache-type-v-draft TYPE        KV cache data type for V for the draft model
                                        allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1
                                        (default: f16)
                                        (env: LLAMA_ARG_CACHE_TYPE_V_DRAFT)


----- sampling params -----

--samplers SAMPLERS                     samplers that will be used for generation in the order, separated by
                                        ';'
                                        (default:
                                        penalties;dry;top_n_sigma;top_k;typ_p;top_p;min_p;xtc;temperature)
-s,    --seed SEED                      RNG seed (default: -1, use random seed for -1)
--sampler-seq, --sampling-seq SEQUENCE
                                        simplified sequence for samplers that will be used (default:
                                        edskypmxt)
--ignore-eos                            ignore end of stream token and continue generating (implies
                                        --logit-bias EOS-inf)
--temp, --temperature N                 temperature (default: 0.80)
--top-k N                               top-k sampling (default: 40, 0 = disabled)
                                        (env: LLAMA_ARG_TOP_K)
--top-p N                               top-p sampling (default: 0.95, 1.0 = disabled)
--min-p N                               min-p sampling (default: 0.05, 0.0 = disabled)
--top-nsigma, --top-n-sigma N           top-n-sigma sampling (default: -1.00, -1.0 = disabled)
--xtc-probability N                     xtc probability (default: 0.00, 0.0 = disabled)
--xtc-threshold N                       xtc threshold (default: 0.10, 1.0 = disabled)
--typical, --typical-p N                locally typical sampling, parameter p (default: 1.00, 1.0 = disabled)
--repeat-last-n N                       last n tokens to consider for penalize (default: 64, 0 = disabled, -1
                                        = ctx_size)
--repeat-penalty N                      penalize repeat sequence of tokens (default: 1.00, 1.0 = disabled)
--presence-penalty N                    repeat alpha presence penalty (default: 0.00, 0.0 = disabled)
--frequency-penalty N                   repeat alpha frequency penalty (default: 0.00, 0.0 = disabled)
--dry-multiplier N                      set DRY sampling multiplier (default: 0.00, 0.0 = disabled)
--dry-base N                            set DRY sampling base value (default: 1.75)
--dry-allowed-length N                  set allowed length for DRY sampling (default: 2)
--dry-penalty-last-n N                  set DRY penalty for the last n tokens (default: -1, 0 = disable, -1 =
                                        context size)
--dry-sequence-breaker STRING           add sequence breaker for DRY sampling, clearing out default breakers
                                        ('\n', ':', '"', '*') in the process; use "none" to not use any
                                        sequence breakers
--adaptive-target N                     adaptive-p: select tokens near this probability (valid range 0.0 to
                                        1.0; negative = disabled) (default: -1.00)
                                        [(more info)](https://github.com/ggml-org/llama.cpp/pull/17927)
--adaptive-decay N                      adaptive-p: decay rate for target adaptation over time. lower values
                                        are more reactive, higher values are more stable.
                                        (valid range 0.0 to 0.99) (default: 0.90)
--dynatemp-range N                      dynamic temperature range (default: 0.00, 0.0 = disabled)
--dynatemp-exp N                        dynamic temperature exponent (default: 1.00)
--mirostat N                            use Mirostat sampling.
                                        Top K, Nucleus and Locally Typical samplers are ignored if used.
                                        (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)
--mirostat-lr N                         Mirostat learning rate, parameter eta (default: 0.10)
--mirostat-ent N                        Mirostat target entropy, parameter tau (default: 5.00)
-l,    --logit-bias TOKEN_ID(+/-)BIAS   modifies the likelihood of token appearing in the completion,
                                        i.e. `--logit-bias 15043+1` to increase likelihood of token ' Hello',
                                        or `--logit-bias 15043-1` to decrease likelihood of token ' Hello'
--grammar GRAMMAR                       BNF-like grammar to constrain generations (see samples in grammars/
                                        dir) (default: '')
--grammar-file FNAME                    file to read grammar from
-j,    --json-schema SCHEMA             JSON schema to constrain generations (https://json-schema.org/), e.g.
                                        `{}` for any JSON object
                                        For schemas w/ external $refs, use --grammar +
                                        example/json_schema_to_grammar.py instead
-jf,   --json-schema-file FILE          File containing a JSON schema to constrain generations
                                        (https://json-schema.org/), e.g. `{}` for any JSON object
                                        For schemas w/ external $refs, use --grammar +
                                        example/json_schema_to_grammar.py instead
-bs,   --backend-sampling               enable backend sampling (experimental) (default: disabled)
                                        (env: LLAMA_ARG_BACKEND_SAMPLING)


----- example-specific params -----

-lcs,  --lookup-cache-static FNAME      path to static lookup cache to use for lookup decoding (not updated by
                                        generation)
-lcd,  --lookup-cache-dynamic FNAME     path to dynamic lookup cache to use for lookup decoding (updated by
                                        generation)
--ctx-checkpoints, --swa-checkpoints N
                                        max number of context checkpoints to create per slot (default:
                                        8)[(more info)](https://github.com/ggml-org/llama.cpp/pull/15293)
                                        (env: LLAMA_ARG_CTX_CHECKPOINTS)
-cram, --cache-ram N                    set the maximum cache size in MiB (default: 8192, -1 - no limit, 0 -
                                        disable)[(more
                                        info)](https://github.com/ggml-org/llama.cpp/pull/16391)
                                        (env: LLAMA_ARG_CACHE_RAM)
-kvu,  --kv-unified, -no-kvu, --no-kv-unified
                                        use single unified KV buffer shared across all sequences (default:
                                        enabled if number of slots is auto)
                                        (env: LLAMA_ARG_KV_UNIFIED)
--context-shift, --no-context-shift     whether to use context shift on infinite text generation (default:
                                        disabled)
                                        (env: LLAMA_ARG_CONTEXT_SHIFT)
-r,    --reverse-prompt PROMPT          halt generation at PROMPT, return control in interactive mode
-sp,   --special                        special tokens output enabled (default: false)
--warmup, --no-warmup                   whether to perform warmup with an empty run (default: enabled)
--spm-infill                            use Suffix/Prefix/Middle pattern for infill (instead of
                                        Prefix/Suffix/Middle) as some models prefer this. (default: disabled)
--pooling {none,mean,cls,last,rank}     pooling type for embeddings, use model default if unspecified
                                        (env: LLAMA_ARG_POOLING)
-np,   --parallel N                     number of server slots (default: -1, -1 = auto)
                                        (env: LLAMA_ARG_N_PARALLEL)
-cb,   --cont-batching, -nocb, --no-cont-batching
                                        whether to enable continuous batching (a.k.a dynamic batching)
                                        (default: enabled)
                                        (env: LLAMA_ARG_CONT_BATCHING)
-mm,   --mmproj FILE                    path to a multimodal projector file. see tools/mtmd/README.md
                                        note: if -hf is used, this argument can be omitted
                                        (env: LLAMA_ARG_MMPROJ)
-mmu,  --mmproj-url URL                 URL to a multimodal projector file. see tools/mtmd/README.md
                                        (env: LLAMA_ARG_MMPROJ_URL)
--mmproj-auto, --no-mmproj, --no-mmproj-auto
                                        whether to use multimodal projector file (if available), useful when
                                        using -hf (default: enabled)
                                        (env: LLAMA_ARG_MMPROJ_AUTO)
--mmproj-offload, --no-mmproj-offload   whether to enable GPU offloading for multimodal projector (default:
                                        enabled)
                                        (env: LLAMA_ARG_MMPROJ_OFFLOAD)
--image-min-tokens N                    minimum number of tokens each image can take, only used by vision
                                        models with dynamic resolution (default: read from model)
                                        (env: LLAMA_ARG_IMAGE_MIN_TOKENS)
--image-max-tokens N                    maximum number of tokens each image can take, only used by vision
                                        models with dynamic resolution (default: read from model)
                                        (env: LLAMA_ARG_IMAGE_MAX_TOKENS)
-otd,  --override-tensor-draft <tensor name pattern>=<buffer type>,...
                                        override tensor buffer type for draft model
-cmoed, --cpu-moe-draft                 keep all Mixture of Experts (MoE) weights in the CPU for the draft
                                        model
                                        (env: LLAMA_ARG_CPU_MOE_DRAFT)
-ncmoed, --n-cpu-moe-draft N            keep the Mixture of Experts (MoE) weights of the first N layers in the
                                        CPU for the draft model
                                        (env: LLAMA_ARG_N_CPU_MOE_DRAFT)
-a,    --alias STRING                   set model name aliases, comma-separated (to be used by API)
                                        (env: LLAMA_ARG_ALIAS)
--tags STRING                           set model tags, comma-separated (informational, not used for routing)
                                        (env: LLAMA_ARG_TAGS)
--host HOST                             ip address to listen, or bind to an UNIX socket if the address ends
                                        with .sock (default: 127.0.0.1)
                                        (env: LLAMA_ARG_HOST)
--port PORT                             port to listen (default: 8080)
                                        (env: LLAMA_ARG_PORT)
--path PATH                             path to serve static files from (default: )
                                        (env: LLAMA_ARG_STATIC_PATH)
--api-prefix PREFIX                     prefix path the server serves from, without the trailing slash
                                        (default: )
                                        (env: LLAMA_ARG_API_PREFIX)
--webui-config JSON                     JSON that provides default WebUI settings (overrides WebUI defaults)
                                        (env: LLAMA_ARG_WEBUI_CONFIG)
--webui-config-file PATH                JSON file that provides default WebUI settings (overrides WebUI
                                        defaults)
                                        (env: LLAMA_ARG_WEBUI_CONFIG_FILE)
--webui, --no-webui                     whether to enable the Web UI (default: enabled)
                                        (env: LLAMA_ARG_WEBUI)
--embedding, --embeddings               restrict to only support embedding use case; use only with dedicated
                                        embedding models (default: disabled)
                                        (env: LLAMA_ARG_EMBEDDINGS)
--rerank, --reranking                   enable reranking endpoint on server (default: disabled)
                                        (env: LLAMA_ARG_RERANKING)
--api-key KEY                           API key to use for authentication, multiple keys can be provided as a
                                        comma-separated list (default: none)
                                        (env: LLAMA_API_KEY)
--api-key-file FNAME                    path to file containing API keys (default: none)
--ssl-key-file FNAME                    path to file a PEM-encoded SSL private key
                                        (env: LLAMA_ARG_SSL_KEY_FILE)
--ssl-cert-file FNAME                   path to file a PEM-encoded SSL certificate
                                        (env: LLAMA_ARG_SSL_CERT_FILE)
--chat-template-kwargs STRING           sets additional params for the json template parser, must be a valid
                                        json object string, e.g. '{"key1":"value1","key2":"value2"}'
                                        (env: LLAMA_CHAT_TEMPLATE_KWARGS)
-to,   --timeout N                      server read/write timeout in seconds (default: 600)
                                        (env: LLAMA_ARG_TIMEOUT)
--threads-http N                        number of threads used to process HTTP requests (default: -1)
                                        (env: LLAMA_ARG_THREADS_HTTP)
--cache-prompt, --no-cache-prompt       whether to enable prompt caching (default: enabled)
                                        (env: LLAMA_ARG_CACHE_PROMPT)
--cache-reuse N                         min chunk size to attempt reusing from the cache via KV shifting,
                                        requires prompt caching to be enabled (default: 0)
                                        [(card)](https://ggml.ai/f0.png)
                                        (env: LLAMA_ARG_CACHE_REUSE)
--metrics                               enable prometheus compatible metrics endpoint (default: disabled)
                                        (env: LLAMA_ARG_ENDPOINT_METRICS)
--props                                 enable changing global properties via POST /props (default: disabled)
                                        (env: LLAMA_ARG_ENDPOINT_PROPS)
--slots, --no-slots                     expose slots monitoring endpoint (default: enabled)
                                        (env: LLAMA_ARG_ENDPOINT_SLOTS)
--slot-save-path PATH                   path to save slot kv cache (default: disabled)
--media-path PATH                       directory for loading local media files; files can be accessed via
                                        file:// URLs using relative paths (default: disabled)
--models-dir PATH                       directory containing models for the router server (default: disabled)
                                        (env: LLAMA_ARG_MODELS_DIR)
--models-preset PATH                    path to INI file containing model presets for the router server
                                        (default: disabled)
                                        (env: LLAMA_ARG_MODELS_PRESET)
--models-max N                          for router server, maximum number of models to load simultaneously
                                        (default: 4, 0 = unlimited)
                                        (env: LLAMA_ARG_MODELS_MAX)
--models-autoload, --no-models-autoload
                                        for router server, whether to automatically load models (default:
                                        enabled)
                                        (env: LLAMA_ARG_MODELS_AUTOLOAD)
--jinja, --no-jinja                     whether to use jinja template engine for chat (default: enabled)
                                        (env: LLAMA_ARG_JINJA)
--reasoning-format FORMAT               controls whether thought tags are allowed and/or extracted from the
                                        response, and in which format they're returned; one of:
                                        - none: leaves thoughts unparsed in `message.content`
                                        - deepseek: puts thoughts in `message.reasoning_content`
                                        - deepseek-legacy: keeps `<think>` tags in `message.content` while
                                        also populating `message.reasoning_content`
                                        (default: auto)
                                        (env: LLAMA_ARG_THINK)
--reasoning-budget N                    controls the amount of thinking allowed; currently only one of: -1 for
                                        unrestricted thinking budget, or 0 to disable thinking (default: -1)
                                        (env: LLAMA_ARG_THINK_BUDGET)
--chat-template JINJA_TEMPLATE          set custom jinja chat template (default: template taken from model's
                                        metadata)
                                        if suffix/prefix are specified, template will be disabled
                                        only commonly used templates are accepted (unless --jinja is set
                                        before this flag):
                                        list of built-in templates:
                                        bailing, bailing-think, bailing2, chatglm3, chatglm4, chatml,
                                        command-r, deepseek, deepseek2, deepseek3, exaone-moe, exaone3,
                                        exaone4, falcon3, gemma, gigachat, glmedge, gpt-oss, granite, grok-2,
                                        hunyuan-dense, hunyuan-moe, kimi-k2, llama2, llama2-sys,
                                        llama2-sys-bos, llama2-sys-strip, llama3, llama4, megrez, minicpm,
                                        mistral-v1, mistral-v3, mistral-v3-tekken, mistral-v7,
                                        mistral-v7-tekken, monarch, openchat, orion, pangu-embedded, phi3,
                                        phi4, rwkv-world, seed_oss, smolvlm, solar-open, vicuna, vicuna-orca,
                                        yandex, zephyr
                                        (env: LLAMA_ARG_CHAT_TEMPLATE)
--chat-template-file JINJA_TEMPLATE_FILE
                                        set custom jinja chat template file (default: template taken from
                                        model's metadata)
                                        if suffix/prefix are specified, template will be disabled
                                        only commonly used templates are accepted (unless --jinja is set
                                        before this flag):
                                        list of built-in templates:
                                        bailing, bailing-think, bailing2, chatglm3, chatglm4, chatml,
                                        command-r, deepseek, deepseek2, deepseek3, exaone-moe, exaone3,
                                        exaone4, falcon3, gemma, gigachat, glmedge, gpt-oss, granite, grok-2,
                                        hunyuan-dense, hunyuan-moe, kimi-k2, llama2, llama2-sys,
                                        llama2-sys-bos, llama2-sys-strip, llama3, llama4, megrez, minicpm,
                                        mistral-v1, mistral-v3, mistral-v3-tekken, mistral-v7,
                                        mistral-v7-tekken, monarch, openchat, orion, pangu-embedded, phi3,
                                        phi4, rwkv-world, seed_oss, smolvlm, solar-open, vicuna, vicuna-orca,
                                        yandex, zephyr
                                        (env: LLAMA_ARG_CHAT_TEMPLATE_FILE)
--prefill-assistant, --no-prefill-assistant
                                        whether to prefill the assistant's response if the last message is an
                                        assistant message (default: prefill enabled)
                                        when this flag is set, if the last message is an assistant message
                                        then it will be treated as a full message and not prefilled

                                        (env: LLAMA_ARG_PREFILL_ASSISTANT)
-sps,  --slot-prompt-similarity SIMILARITY
                                        how much the prompt of a request must match the prompt of a slot in
                                        order to use that slot (default: 0.10, 0.0 = disabled)
--lora-init-without-apply               load LoRA adapters without applying them (apply later via POST
                                        /lora-adapters) (default: disabled)
--sleep-idle-seconds SECONDS            number of seconds of idleness after which the server will sleep
                                        (default: -1; -1 = disabled)
-td,   --threads-draft N                number of threads to use during generation (default: same as
                                        --threads)
-tbd,  --threads-batch-draft N          number of threads to use during batch and prompt processing (default:
                                        same as --threads-draft)
--draft, --draft-n, --draft-max N       number of tokens to draft for speculative decoding (default: 16)
                                        (env: LLAMA_ARG_DRAFT_MAX)
--draft-min, --draft-n-min N            minimum number of draft tokens to use for speculative decoding
                                        (default: 0)
                                        (env: LLAMA_ARG_DRAFT_MIN)
--draft-p-min P                         minimum speculative decoding probability (greedy) (default: 0.75)
                                        (env: LLAMA_ARG_DRAFT_P_MIN)
-cd,   --ctx-size-draft N               size of the prompt context for the draft model (default: 0, 0 = loaded
                                        from model)
                                        (env: LLAMA_ARG_CTX_SIZE_DRAFT)
-devd, --device-draft <dev1,dev2,..>    comma-separated list of devices to use for offloading the draft model
                                        (none = don't offload)
                                        use --list-devices to see a list of available devices
-ngld, --gpu-layers-draft, --n-gpu-layers-draft N
                                        max. number of draft model layers to store in VRAM, either an exact
                                        number, 'auto', or 'all' (default: auto)
                                        (env: LLAMA_ARG_N_GPU_LAYERS_DRAFT)
-md,   --model-draft FNAME              draft model for speculative decoding (default: unused)
                                        (env: LLAMA_ARG_MODEL_DRAFT)
--spec-replace TARGET DRAFT             translate the string in TARGET into DRAFT if the draft model and main
                                        model are not compatible
--spec-type [none|ngram-cache|ngram-simple|ngram-map-k|ngram-map-k4v|ngram-mod]
                                        type of speculative decoding to use when no draft model is provided
                                        (default: none)
--spec-ngram-size-n N                   ngram size N for ngram-simple/ngram-map speculative decoding, length
                                        of lookup n-gram (default: 12)
--spec-ngram-size-m N                   ngram size M for ngram-simple/ngram-map speculative decoding, length
                                        of draft m-gram (default: 48)
--spec-ngram-min-hits N                 minimum hits for ngram-map speculative decoding (default: 1)
-mv,   --model-vocoder FNAME            vocoder model for audio generation (default: unused)
--tts-use-guide-tokens                  Use guide tokens to improve TTS word recall
--embd-gemma-default                    use default EmbeddingGemma model (note: can download weights from the
                                        internet)
--fim-qwen-1.5b-default                 use default Qwen 2.5 Coder 1.5B (note: can download weights from the
                                        internet)
--fim-qwen-3b-default                   use default Qwen 2.5 Coder 3B (note: can download weights from the
                                        internet)
--fim-qwen-7b-default                   use default Qwen 2.5 Coder 7B (note: can download weights from the
                                        internet)
--fim-qwen-7b-spec                      use Qwen 2.5 Coder 7B + 0.5B draft for speculative decoding (note: can
                                        download weights from the internet)
--fim-qwen-14b-spec                     use Qwen 2.5 Coder 14B + 0.5B draft for speculative decoding (note:
                                        can download weights from the internet)
--fim-qwen-30b-default                  use default Qwen 3 Coder 30B A3B Instruct (note: can download weights
                                        from the internet)
--gpt-oss-20b-default                   use gpt-oss-20b (note: can download weights from the internet)
--gpt-oss-120b-default                  use gpt-oss-120b (note: can download weights from the internet)
--vision-gemma-4b-default               use Gemma 3 4B QAT (note: can download weights from the internet)
--vision-gemma-12b-default              use Gemma 3 12B QAT (note: can download weights from the internet)

Apr 15 20:08:59 locaal pkg[8607]: ggml-0.9.8 installed
Apr 15 20:09:00 locaal pkg[8607]: llama-cpp-8182 installed

You installed LLaMA-cpp: Facebook's LLaMA model runner.

In order to experience LLaMA-cpp please download some
AI model in the GGUF format, for example from huggingface.com,
run the script below, and open localhost:9011 in your browser
to communicate with this AI model.

$ llama-server -m $MODEL \
  --host 0.0.0.0 \
  --port 9011 \
  -ngl 15

or

you can add the following lines to /etc/rc.conf,
start the llama-server service,
and navigate to http://localhost:8080:
> llama_server_enable=YES
> llama_server_model=/path/to/models/llama-2-7b-chat.Q4_K_M.gguf
> llama_server_args="--device Vulkan0 -ngl 27"

root@locaal:~ # nvidia-smi
Sun Apr 12 13:10:37 2026       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 595.58.03              Driver Version: 595.58.03      CUDA Version: N/A      |
+-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA GeForce RTX 3060        Off |   00000000:06:00.0 Off |                  N/A |
|  0%   51C    P8             17W /  170W |       1MiB /  12288MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

root@locaal:~ # freebsd-version -ku
13.5-RELEASE-p10
13.5-RELEASE-p11

root@locaal:~ # uname -a
FreeBSD locaal 13.5-RELEASE-p10 FreeBSD 13.5-RELEASE-p10 GENERIC amd64

root@locaal:~ # freebsd-update fetch
src component not installed, skipped
[..]
The following files will be updated as part of updating to
13.5-RELEASE-p11:
/bin/freebsd-version
/boot/kernel/kgssapi.ko
/usr/lib/librpcsec_gss.a
/usr/lib/librpcsec_gss.so.1
/usr/lib32/librpcsec_gss.a
/usr/lib32/librpcsec_gss.so.1

WARNING: FreeBSD 13.5-RELEASE-p10 is approaching its End-of-Life date.
It is strongly recommended that you upgrade to a newer
release within the next 2 weeks.

root@locaal:~ # freebsd-update install
src component not installed, skipped
Installing updates...
Restarting sshd after upgrade
Performing sanity check on sshd configuration.
Stopping sshd.
Waiting for PIDS: 1140.
Performing sanity check on sshd configuration.
Starting sshd.
Scanning //usr/share/certs/blacklisted for certificates...
Scanning //usr/share/certs/trusted for certificates...
 done.

Apr 12 12:23:36 locaal pkg[54164]: pkg upgraded: 2.5.1 -> 2.6.2_1 
Apr 12 12:40:44 locaal pkg[54197]: aom upgraded: 3.13.1 -> 3.13.2 
Apr 12 12:40:44 locaal pkg[54197]: auto-admin upgraded: 0.8.4.6 -> 0.8.4.24 
Apr 12 12:40:44 locaal pkg[54197]: dav1d upgraded: 1.5.3 -> 1.5.3_1 
Apr 12 12:40:44 locaal pkg[54197]: highway-1.3.0 installed
Apr 12 12:40:45 locaal pkg[54197]: hwdata upgraded: 0.403,1 -> 0.405,1 
Apr 12 12:40:45 locaal pkg[54197]: jansson upgraded: 2.14.1 -> 2.15.0 
Apr 12 12:40:45 locaal pkg[54197]: lame-3.100_5 installed
Apr 12 12:40:45 locaal pkg[54197]: lcms2 upgraded: 2.17 -> 2.18 
Apr 12 12:40:45 locaal pkg[54197]: libdvdread-7.0.0 installed
Apr 12 12:40:45 locaal pkg[54197]: libdvdnav-7.0.0 installed
Apr 12 12:40:45 locaal pkg[54197]: libfontenc upgraded: 1.1.8 -> 1.1.9 
Apr 12 12:40:45 locaal pkg[54197]: libimagequant upgraded: 4.4.1_1 -> 4.4.1_3 
Apr 12 12:40:45 locaal pkg[54197]: libogg-1.3.6,4 installed
Apr 12 12:40:46 locaal pkg[54197]: flac-1.5.0,1 installed
Apr 12 12:40:46 locaal pkg[54197]: libudfread-1.2.0 installed
Apr 12 12:40:46 locaal pkg[54197]: libunibreak-6.1,1 installed
Apr 12 12:40:46 locaal pkg[54197]: libunistring upgraded: 1.4.1 -> 1.4.2 
Apr 12 12:40:46 locaal pkg[54197]: libidn2 reinstalled: 2.3.8 -> 2.3.8 
Apr 12 12:40:46 locaal pkg[54197]: libpsl reinstalled: 0.21.5_2 -> 0.21.5_2 
Apr 12 12:40:46 locaal pkg[54197]: libuv upgraded: 1.51.0 -> 1.52.0 
Apr 12 12:40:46 locaal pkg[54197]: libv4l-1.23.0_5 installed
Apr 12 12:40:46 locaal pkg[54197]: libvorbis-1.3.7_2,3 installed
Apr 12 12:40:47 locaal pkg[54197]: libvpx-1.16.0 installed
Apr 12 12:40:47 locaal pkg[54197]: libx264-0.164.3095 installed
Apr 12 12:40:51 locaal pkg[54197]: libxcb reinstalled: 1.17.0 -> 1.17.0 
Apr 12 12:40:52 locaal pkg[54197]: libX11 upgraded: 1.8.12,1 -> 1.8.13,1 
Apr 12 12:40:53 locaal pkg[54197]: libXext reinstalled: 1.3.6,1 -> 1.3.6,1 
Apr 12 12:40:53 locaal pkg[54197]: libXt reinstalled: 1.3.0,1 -> 1.3.0,1 
Apr 12 12:40:53 locaal pkg[54197]: libXmu reinstalled: 1.1.4,1 -> 1.1.4,1 
Apr 12 12:40:53 locaal pkg[54197]: libXv reinstalled: 1.0.13,1 -> 1.0.13,1 
Apr 12 12:40:53 locaal pkg[54197]: libglvnd reinstalled: 1.7.0 -> 1.7.0 
Apr 12 12:40:53 locaal pkg[54197]: libvdpau-1.5 installed
Apr 12 12:41:06 locaal pkg[54197]: linux-nvidia-libs upgraded: 580.119.02 -> 595.58.03 
Apr 12 12:41:06 locaal pkg[54197]: llhttp upgraded: 9.3.0 -> 9.3.1 
Apr 12 12:41:06 locaal pkg[54197]: libgit2 reinstalled: 1.9.2 -> 1.9.2 
Apr 12 12:41:06 locaal pkg[54197]: mpfr reinstalled: 4.2.2,1 -> 4.2.2,1 
Apr 12 12:41:06 locaal pkg[54197]: mpc upgraded: 1.3.1_1 -> 1.4.0 
Apr 12 12:41:06 locaal pkg[54197]: mpg123-1.33.4 installed
Apr 12 12:41:06 locaal pkg[54197]: nss upgraded: 3.121 -> 3.122 
Apr 12 12:41:08 locaal pkg[54197]: nvidia-kmod upgraded: 580.119.02.1305000_1 -> 595.58.03.1305000 
Apr 12 12:41:08 locaal pkg[54197]: nvidia-drm-510-kmod upgraded: 580.119.02.1305000 -> 595.58.03.1305000 
Apr 12 12:41:15 locaal pkg[54197]: ollama upgraded: 0.13.5_3 -> 0.19.0_2 
Apr 12 12:41:15 locaal pkg[54197]: openjph-0.26.3 installed
Apr 12 12:41:15 locaal pkg[54197]: opus-1.6.1 installed
Apr 12 12:41:16 locaal pkg[54197]: libsndfile-1.2.2_2 installed
Apr 12 12:41:16 locaal pkg[54197]: pciids upgraded: 20251223 -> 20260309 
Apr 12 12:41:18 locaal pkg[54197]: pkg reinstalled: 2.6.2_1 -> 2.6.2_1 
Apr 12 12:41:18 locaal pkg[54197]: pytorch-2.8.0_1 deinstalled
Apr 12 12:41:19 locaal pkg[54197]: shaderc upgraded: 2025.5_1 -> 2026.1 
Apr 12 12:41:21 locaal pkg[54197]: shimmy upgraded: 1.9.0 -> 1.9.0_2 
Apr 12 12:41:21 locaal pkg[54197]: spdlog upgraded: 1.16.0_1 -> 1.17.0 
Apr 12 12:41:22 locaal pkg[54197]: level-zero upgraded: 1.26.3 -> 1.28.0 
Apr 12 12:41:22 locaal pkg[54197]: spirv-tools upgraded: 2025.5 -> 2026.1 
Apr 12 12:41:22 locaal pkg[54197]: glslang upgraded: 16.1.0_1 -> 16.2.0 
Apr 12 12:41:22 locaal pkg[54197]: suitesparse-config upgraded: 7.12.1 -> 7.12.2 
Apr 12 12:41:22 locaal pkg[54197]: svt-av1-4.1.0 installed
Apr 12 12:41:23 locaal pkg[54197]: wolfssl-5.9.0 installed
Apr 12 12:41:23 locaal pkg[54197]: x265-4.1 installed
Apr 12 12:41:23 locaal pkg[54197]: xxhash-0.8.3 installed
Apr 12 12:41:23 locaal pkg[54197]: libplacebo-7.360.1 installed
Apr 12 12:41:23 locaal pkg[54197]: zlib-ng-2.3.3 installed
Apr 12 12:41:23 locaal pkg[54197]: gdal-3.11.5_2 deinstalled
Apr 12 12:41:23 locaal pkg[54197]: expat upgraded: 2.7.4 -> 2.7.5 
Apr 12 12:41:30 locaal pkg[54197]: cmake-core upgraded: 3.31.10 -> 3.31.10_1 
Apr 12 12:41:30 locaal pkg[54197]: freexl reinstalled: 2.0.0 -> 2.0.0 
Apr 12 12:41:30 locaal pkg[54197]: libaec upgraded: 1.1.4 -> 1.1.5 
Apr 12 12:41:30 locaal pkg[54197]: postgresql17-client-17.9 deinstalled
Apr 12 12:41:31 locaal pkg[54197]: gettext-runtime upgraded: 0.26 -> 1.0 
Apr 12 12:41:31 locaal pkg[54197]: bash-5.3.9 installed
Apr 12 12:41:31 locaal pkg[54197]: libXpm reinstalled: 3.5.17_1 -> 3.5.17_1 
Apr 12 12:41:32 locaal pkg[54197]: libXaw reinstalled: 1.0.16,2 -> 1.0.16,2 
Apr 12 12:41:32 locaal pkg[54197]: libgpg-error upgraded: 1.58 -> 1.59 
Apr 12 12:41:32 locaal pkg[54197]: libassuan reinstalled: 3.0.2 -> 3.0.2 
Apr 12 12:41:32 locaal pkg[54197]: gpgme reinstalled: 2.0.1 -> 2.0.1 
Apr 12 12:41:32 locaal pkg[54197]: gpgmepp reinstalled: 2.0.0 -> 2.0.0 
Apr 12 12:41:32 locaal pkg[54197]: libgcrypt upgraded: 1.11.2 -> 1.12.0_1 
Apr 12 12:41:35 locaal pkg[54197]: postgresql18-client-18.3 installed
Apr 12 12:41:35 locaal pkg[54197]: srt-1.5.4 installed
Apr 12 12:41:35 locaal pkg[54197]: wayland reinstalled: 1.24.0_2 -> 1.24.0_2 
Apr 12 12:41:35 locaal pkg[54197]: egl-wayland upgraded: 1.1.20 -> 1.1.21 
Apr 12 12:41:35 locaal pkg[54197]: libva-2.23.0 installed
Apr 12 12:41:35 locaal pkg[54197]: mesa-libs reinstalled: 24.1.7_1 -> 24.1.7_1 
Apr 12 12:41:35 locaal pkg[54197]: egl-wayland2-1.0.1 installed
Apr 12 12:41:35 locaal pkg[54197]: egl-x11 upgraded: 1.0.4 -> 1.0.5 
Apr 12 12:41:50 locaal pkg[54197]: nvidia-driver upgraded: 580.119.02_1 -> 595.58.03 
Apr 12 12:41:50 locaal pkg[54197]: nvidia-drm-kmod upgraded: 580.119.02 -> 595.58.03 
Apr 12 12:41:50 locaal pkg[54197]: py311-torchaudio-2.8.0_3 deinstalled
Apr 12 12:41:50 locaal pkg[54197]: py311-torchvision-0.23.0_2 deinstalled
Apr 12 12:41:50 locaal pkg[54197]: png upgraded: 1.6.53 -> 1.6.55 
Apr 12 12:41:50 locaal pkg[54197]: freetype2 upgraded: 2.14.1 -> 2.14.3 
Apr 12 12:41:50 locaal pkg[54197]: cairo reinstalled: 1.18.2,3 -> 1.18.2,3 
Apr 12 12:41:51 locaal pkg[54197]: gdk-pixbuf2 reinstalled: 2.44.1 -> 2.44.1 
Apr 12 12:41:52 locaal pkg[54197]: harfbuzz upgraded: 12.3.0 -> 13.2.1 
Apr 12 12:41:52 locaal pkg[54197]: libXft reinstalled: 2.3.8 -> 2.3.8 
Apr 12 12:41:52 locaal pkg[54197]: libass-0.17.4 installed
Apr 12 12:41:52 locaal pkg[54197]: libavif upgraded: 1.3.0_2 -> 1.3.0_3 
Apr 12 12:41:52 locaal pkg[54197]: libbluray-1.4.1,1 installed
Apr 12 12:41:52 locaal pkg[54197]: libraqm reinstalled: 0.10.3 -> 0.10.3 
Apr 12 12:41:52 locaal pkg[54197]: openjpeg upgraded: 2.5.4_1 -> 2.5.4_2 
Apr 12 12:41:54 locaal pkg[54197]: pango upgraded: 1.56.4 -> 1.56.4_1 
Apr 12 12:41:55 locaal pkg[54197]: librsvg2-rust-2.62.0_1 installed
Apr 12 12:41:55 locaal pkg[54197]: poppler upgraded: 25.10.0 -> 25.10.0_1 
Apr 12 12:41:55 locaal pkg[54197]: tk86 reinstalled: 8.6.17 -> 8.6.17 
Apr 12 12:41:56 locaal pkg[54197]: webp reinstalled: 1.6.0 -> 1.6.0 
Apr 12 12:41:56 locaal pkg[54197]: libgd reinstalled: 2.3.3_13,1 -> 2.3.3_13,1 
Apr 12 12:41:56 locaal pkg[54197]: graphviz upgraded: 14.1.1 -> 14.1.4 
Apr 12 12:41:56 locaal pkg[54197]: xterm upgraded: 406 -> 407 
Apr 12 12:41:57 locaal pkg[54197]: py311-pytorch-2.8.0_4 deinstalled
Apr 12 12:41:57 locaal pkg[54197]: openmpi4-4.1.8_1 deinstalled
Apr 12 12:41:58 locaal pkg[54197]: protobuf upgraded: 29.5,1 -> 29.6,1 
Apr 12 12:41:58 locaal pkg[54197]: onnx upgraded: 1.19.1_1 -> 1.19.1_2 
Apr 12 12:41:58 locaal pkg[54197]: pthreadpool upgraded: 0.1.126 -> 0.1.147 
Apr 12 12:42:14 locaal pkg[54197]: python311 upgraded: 3.11.15 -> 3.11.15_1 
Apr 12 12:42:17 locaal pkg[54197]: py311-Babel upgraded: 2.17.0_1 -> 2.18.0 
Apr 12 12:42:17 locaal pkg[54197]: py311-anyio upgraded: 4.12.0 -> 4.12.1 
Apr 12 12:42:17 locaal pkg[54197]: py311-boost-libs-1.89.0 installed
Apr 12 12:42:17 locaal pkg[54197]: py311-cffi upgraded: 1.17.1 -> 2.0.0 
Apr 12 12:42:18 locaal pkg[54197]: py311-dill upgraded: 0.4.0 -> 0.4.1 
Apr 12 12:42:18 locaal pkg[54197]: py311-filelock upgraded: 3.20.1 -> 3.25.0 
Apr 12 12:42:18 locaal pkg[54197]: py311-fsspec upgraded: 2025.12.0 -> 2026.2.0 
Apr 12 12:42:18 locaal pkg[54197]: py311-jiter upgraded: 0.12.0_1 -> 0.13.0_1 
Apr 12 12:42:18 locaal pkg[54197]: py311-kiwisolver upgraded: 1.4.9,1 -> 1.5.0,1 
Apr 12 12:42:18 locaal pkg[54197]: py311-librt upgraded: 0.7.2 -> 0.8.0 
Apr 12 12:42:18 locaal pkg[54197]: py311-maturin upgraded: 1.10.2_1 -> 1.12.6_1 
Apr 12 12:42:19 locaal pkg[54197]: py311-mpmath upgraded: 1.3.0_2 -> 1.4.1 
Apr 12 12:42:47 locaal pkg[54197]: py311-numpy upgraded: 1.26.4_11,1 -> 1.26.4_12,1 
Apr 12 12:42:54 locaal pkg[54197]: Imath-3.2.2_2 installed
Apr 12 12:42:55 locaal pkg[54197]: openexr-3.4.8 installed
Apr 12 12:42:55 locaal pkg[54197]: libjxl-0.11.2 installed
Apr 12 12:42:57 locaal pkg[54197]: ffmpeg-8.1,1 installed
Apr 12 12:42:57 locaal pkg[54197]: py311-SoundFile-0.13.1 installed
Apr 12 12:42:57 locaal pkg[54197]: py311-bottleneck upgraded: 1.3.8_1 -> 1.6.0 
Apr 12 12:42:57 locaal pkg[54197]: py311-orjson upgraded: 3.11.4_1 -> 3.11.4_3 
Apr 12 12:42:57 locaal pkg[54197]: py311-packaging upgraded: 25.0 -> 26.0 
Apr 12 12:42:57 locaal pkg[54197]: py311-pathspec upgraded: 1.0.3 -> 1.0.4 
Apr 12 12:42:58 locaal pkg[54197]: py311-pillow upgraded: 11.3.0_1 -> 11.3.0_2 
Apr 12 12:42:58 locaal pkg[54197]: py311-liquidctl upgraded: 1.15.0_1 -> 1.16.0 
Apr 12 12:42:58 locaal pkg[54197]: py311-protobuf upgraded: 6.33.2,1 -> 6.33.5,1 
Apr 12 12:42:58 locaal pkg[54197]: py311-psutil upgraded: 7.1.3 -> 7.2.2 
Apr 12 12:42:58 locaal pkg[54197]: py311-puremagic upgraded: 1.24_1 -> 1.30_1 
Apr 12 12:42:59 locaal pkg[54197]: py311-pydantic-core upgraded: 2.41.5_2 -> 2.41.5_4 
Apr 12 12:42:59 locaal pkg[54197]: py311-pygit2 upgraded: 1.18.2 -> 1.19.1 
Apr 12 12:42:59 locaal pkg[54197]: py311-pyparsing upgraded: 3.3.0 -> 3.3.2 
Apr 12 12:42:59 locaal pkg[54197]: py311-regex upgraded: 2025.11.3 -> 2026.2.28 
Apr 12 12:43:15 locaal pkg[54197]: py311-scipy upgraded: 1.11.1_4,1 -> 1.11.1_5,1 
Apr 12 12:43:35 locaal pkg[54197]: py311-sympy upgraded: 1.14.0 -> 1.14.0_1 
Apr 12 12:43:35 locaal pkg[54197]: py311-tqdm upgraded: 4.67.1 -> 4.67.3 
Apr 12 12:43:53 locaal pkg[54197]: py311-openai upgraded: 1.109.1 -> 2.28.0 
Apr 12 12:43:53 locaal pkg[54197]: py311-types-setuptools upgraded: 80.9.0.20251223 -> 82.0.0.20260210 
Apr 12 12:43:54 locaal pkg[54197]: py311-tzdata upgraded: 2025.3 -> 2026.1 
Apr 12 12:43:54 locaal pkg[54197]: py311-unicodedata2 upgraded: 17.0.0 -> 17.0.1 
Apr 12 12:43:54 locaal pkg[54197]: py311-urllib3 upgraded: 2.6.2,1 -> 2.6.3,1 
Apr 12 12:43:54 locaal pkg[54197]: py311-wheel upgraded: 0.45.1 -> 0.46.3_1 
Apr 12 12:43:54 locaal pkg[54197]: py311-zopfli upgraded: 0.4.0 -> 0.4.1 
Apr 12 12:43:56 locaal pkg[54197]: py311-fonttools upgraded: 4.61.1 -> 4.61.1_1 
Apr 12 12:43:58 locaal pkg[54197]: py311-matplotlib upgraded: 3.8.0_2 -> 3.10.8 
Apr 12 12:43:58 locaal pkg[54197]: py311-certifi upgraded: 2025.11.12 -> 2026.1.4 
Apr 12 12:44:02 locaal pkg[54197]: py311-networkx upgraded: 3.5_3,2 -> 3.6,2 
Apr 12 12:44:02 locaal pkg[54197]: slurm-wlm-25.11.0_1 deinstalled
Apr 12 12:44:04 locaal pkg[54197]: hwloc2 reinstalled: 2.12.1_1 -> 2.12.1_1 
Apr 12 12:44:04 locaal pkg[54197]: munge upgraded: 0.5.17 -> 0.5.18 
Apr 12 12:44:04 locaal pkg[54197]: mysql80-client-8.0.44 deinstalled
Apr 12 12:44:05 locaal pkg[54197]: curl upgraded: 8.17.0 -> 8.19.0_1 
Apr 12 12:44:05 locaal pkg[54197]: librdkafka reinstalled: 2.8.0 -> 2.8.0 
Apr 12 12:44:05 locaal pkg[54197]: netcdf reinstalled: 4.9.3 -> 4.9.3 
Apr 12 12:44:09 locaal pkg[54197]: gdal-3.11.5_2 installed
Apr 12 12:44:11 locaal pkg[54197]: onetbb upgraded: 2022.3.0_1 -> 2022.3.0_3 
Apr 12 12:44:13 locaal pkg[54197]: openldap26-client upgraded: 2.6.10_1 -> 2.6.13 
Apr 12 12:44:26 locaal pkg[54197]: perl5 upgraded: 5.42.0_1 -> 5.42.2 
Apr 12 12:44:28 locaal pkg[54197]: groff upgraded: 1.23.0_5 -> 1.24.1_1 
Apr 12 12:45:15 locaal pkg[54197]: llvm15 reinstalled: 15.0.7_10 -> 15.0.7_10 
Apr 12 12:46:11 locaal pkg[54197]: llvm19 reinstalled: 19.1.7_1 -> 19.1.7_1 
Apr 12 12:46:12 locaal pkg[54197]: mysql84-client-8.4.8 installed
Apr 12 12:46:13 locaal pkg[54197]: slurm-wlm-25.11.4 installed
Apr 12 12:46:14 locaal pkg[54197]: p5-IO-Socket-SSL upgraded: 2.095 -> 2.098 
Apr 12 12:46:27 locaal pkg[54197]: git upgraded: 2.52.0 -> 2.53.0 
Apr 12 12:46:28 locaal pkg[54197]: p5-TimeDate upgraded: 2.33,1 -> 2.35,1 
Apr 12 12:46:30 locaal pkg[54197]: pmix-5.0.9 installed
Apr 12 12:46:31 locaal pkg[54197]: prrte-3.0.12 installed
Apr 12 12:46:35 locaal pkg[54197]: openmpi-5.0.9_1 installed
Apr 12 12:47:38 locaal pkg[54197]: py311-pytorch-2.10.0_2 installed
Apr 12 12:47:39 locaal pkg[54197]: py311-torchvision-0.25.0 installed
Apr 12 12:47:39 locaal pkg[54197]: py311-torchcodec-0.10.0_1 installed
Apr 12 12:47:39 locaal pkg[54197]: py311-torchaudio-2.10.0_1 installed
Apr 12 12:50:05 locaal pkg[54197]: rust upgraded: 1.92.0 -> 1.94.0 
Apr 12 12:50:06 locaal pkg[54197]: spirv-llvm-translator-llvm15 upgraded: 15.0.19 -> 15.0.22 
Apr 12 12:50:06 locaal pkg[54197]: spirv-llvm-translator-llvm19 upgraded: 19.1.14 -> 19.1.17 
Apr 12 12:50:06 locaal pkg[54197]: mesa-dri upgraded: 24.1.7_10 -> 24.1.7_11