github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2809] Ollama does not utilise Nvidia GPU. #1701

New Issue
Closed
opened 2026-04-12 11:40:37 -05:00 by GiteaMirror · 10 comments
GiteaMirror commented 2026-04-12 11:40:37 -05:00
Owner
Copy Link

Originally created by @rohitranjan-2702 on GitHub (Feb 28, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2809

Originally assigned to: @dhiltgen on GitHub.

Currently I am trying to run the llama-2 model locally on WSL via docker image with gpus-all flag. Still it does not utilise my Nvidia GPU.

image

Originally created by @rohitranjan-2702 on GitHub (Feb 28, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2809 Originally assigned to: @dhiltgen on GitHub. Currently I am trying to run the llama-2 model locally on WSL via docker image with `gpus-all` flag. Still it does not utilise my Nvidia GPU. ![image](https://github.com/ollama/ollama/assets/68217537/18e4f9f6-a0e9-48b7-bfe4-ada9dba44edd)
GiteaMirror commented 2026-04-12 11:40:38 -05:00
Author
Owner
Copy Link

@nejib1 commented on GitHub (Feb 28, 2024):

The model is bigger than your GPU...

<!-- gh-comment-id:1969150837 --> @nejib1 commented on GitHub (Feb 28, 2024): The model is bigger than your GPU...
GiteaMirror commented 2026-04-12 11:40:39 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 11, 2024):

We now support native windows which might be an option for you.

If you still want to use Docker, have you followed the NVIDIA WSL setup instructions?

https://docs.nvidia.com/cuda/wsl-user-guide/index.html

If you have followed those instructions, can you share the server log from the container so we can see more information about why it's not loading the GPU? It may be helpful to set -e OLLAMA_DEBUG=1 to the ollama server container to turn on debug logging.

<!-- gh-comment-id:1989412410 --> @dhiltgen commented on GitHub (Mar 11, 2024): We now support native windows which might be an option for you. If you still want to use Docker, have you followed the NVIDIA WSL setup instructions? https://docs.nvidia.com/cuda/wsl-user-guide/index.html If you have followed those instructions, can you share the server log from the container so we can see more information about why it's not loading the GPU? It may be helpful to set `-e OLLAMA_DEBUG=1` to the ollama server container to turn on debug logging.
GiteaMirror commented 2026-04-12 11:40:39 -05:00
Author
Owner
Copy Link

@continue47 commented on GitHub (Mar 25, 2024):

Make sure you are using the latest image of ollama. If you enter the container and type ollama --version you should see the version you are on; compare it with the latest release (currently 0.1.29), if you're not on the latest one, you can update your image with docker-compose pull and docker-compose up -d --force-recreate

<!-- gh-comment-id:2018083085 --> @continue47 commented on GitHub (Mar 25, 2024): Make sure you are using the latest image of ollama. If you enter the container and type `ollama --version` you should see the version you are on; compare it with the latest release (currently 0.1.29), if you're not on the latest one, you can update your image with `docker-compose pull` and `docker-compose up -d --force-recreate`
GiteaMirror commented 2026-04-12 11:40:40 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 12, 2024):

If you're still having problems, please let us know.

<!-- gh-comment-id:2052627789 --> @dhiltgen commented on GitHub (Apr 12, 2024): If you're still having problems, please let us know.
GiteaMirror commented 2026-04-12 11:40:41 -05:00
Author
Owner
Copy Link

@praharshbhatt commented on GitHub (Jun 7, 2024):

Hi all,
I am running into the same issue, in docker, as well as while doing ollama serve.
ollama --version gives:
ollama version is 0.1.4
image

I've tried with:
llama3:8b
mistral:7.2b
llama-2-13b-chat GGUF.

Thanks

<!-- gh-comment-id:2153910177 --> @praharshbhatt commented on GitHub (Jun 7, 2024): Hi all, I am running into the same issue, in docker, as well as while doing `ollama serve`. `ollama --version` gives: `ollama version is 0.1.4` ![image](https://github.com/ollama/ollama/assets/30700808/0fe0160c-c282-4625-ac57-5d16118ed0e3) I've tried with: llama3:8b mistral:7.2b llama-2-13b-chat GGUF. Thanks
GiteaMirror commented 2026-04-12 11:40:41 -05:00
Author
Owner
Copy Link

@praharshbhatt commented on GitHub (Jun 7, 2024):

Update- reinstalled Nvidia toolking, after uninstallking citrix. It turns our, citrix was causing this issue.
image

<!-- gh-comment-id:2154907153 --> @praharshbhatt commented on GitHub (Jun 7, 2024): Update- reinstalled Nvidia toolking, after uninstallking citrix. It turns our, citrix was causing this issue. ![image](https://github.com/ollama/ollama/assets/30700808/63ca37bb-6d85-4813-a16b-88a7d7f5b1ec)
GiteaMirror commented 2026-04-12 11:40:42 -05:00
Author
Owner
Copy Link

@praharshbhatt commented on GitHub (Jun 17, 2024):

update 2: the GPu only gets used while running llama 2 13b gguf.
While testing on llama3:8b and mistral / mythomax, the GPU is not used at all @dhiltgen

<!-- gh-comment-id:2173968441 --> @praharshbhatt commented on GitHub (Jun 17, 2024): update 2: the GPu only gets used while running `llama 2 13b gguf`. While testing on llama3:8b and mistral / mythomax, the GPU is not used at all @dhiltgen
GiteaMirror commented 2026-04-12 11:40:43 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 18, 2024):

@praharshbhatt please make sure you're running the latest version of Ollama and if you're still seeing problems, share your server log.

<!-- gh-comment-id:2176525396 --> @dhiltgen commented on GitHub (Jun 18, 2024): @praharshbhatt please make sure you're running the latest version of Ollama and if you're still seeing problems, share your server log.
GiteaMirror commented 2026-04-12 11:40:43 -05:00
Author
Owner
Copy Link

@praharshbhatt commented on GitHub (Jun 22, 2024):

ollama version is 0.1.40

Created the docker using:

sudo docker run -d \
  -v ollama:/root/.ollama \
  -p 11434:11434 \
  -e OLLAMA_ORIGINS="app://obsidian.md*" \
  --gpus=all \
  --name ollama ollama/ollama

logs:

time=2024-06-22T18:12:29.447Z level=INFO source=server.go:341 msg="starting llama server" cmd="/tmp/ollama1711348412/runners/cpu_avx2/ollama_llama_server --model /root/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 2048 --batch-size 512 --embedding --log-disable --parallel 1 --port 38033"
time=2024-06-22T18:12:29.448Z level=INFO source=sched.go:338 msg="loaded runners" count=1
time=2024-06-22T18:12:29.448Z level=INFO source=server.go:529 msg="waiting for llama runner to start responding"
time=2024-06-22T18:12:29.448Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server error"
INFO [main] build info | build=1 commit="5921b8f" tid="139712474826624" timestamp=1719079949
INFO [main] system info | n_threads=8 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="139712474826624" timestamp=1719079949 total_threads=16
INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="15" port="38033" tid="139712474826624" timestamp=1719079949
llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = llama
llama_model_loader: - kv   1:                               general.name str              = Meta-Llama-3-8B-Instruct
llama_model_loader: - kv   2:                          llama.block_count u32              = 32
llama_model_loader: - kv   3:                       llama.context_length u32              = 8192
llama_model_loader: - kv   4:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv   6:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv   7:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv   8:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  10:                          general.file_type u32              = 2
llama_model_loader: - kv  11:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  12:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 128009
llama_model_loader: - kv  20:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv  21:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q4_0:  225 tensors
llama_model_loader: - type q6_K:    1 tensors
time=2024-06-22T18:12:29.698Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 1.5928 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 128256
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: n_ctx_train      = 8192
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 4
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 14336
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx  = 8192
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: model type       = 8B
llm_load_print_meta: model ftype      = Q4_0
llm_load_print_meta: model params     = 8.03 B
llm_load_print_meta: model size       = 4.33 GiB (4.64 BPW) 
llm_load_print_meta: general.name     = Meta-Llama-3-8B-Instruct
llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
llm_load_tensors: ggml ctx size =    0.15 MiB
llm_load_tensors:        CPU buffer size =  4437.80 MiB
llama_new_context_with_model: n_ctx      = 2048
llama_new_context_with_model: n_batch    = 512
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base  = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init:        CPU KV buffer size =   256.00 MiB
llama_new_context_with_model: KV self size  =  256.00 MiB, K (f16):  128.00 MiB, V (f16):  128.00 MiB
llama_new_context_with_model:        CPU  output buffer size =     0.50 MiB
llama_new_context_with_model:        CPU compute buffer size =   258.50 MiB
llama_new_context_with_model: graph nodes  = 1030
llama_new_context_with_model: graph splits = 1
INFO [main] model loaded | tid="139712474826624" timestamp=1719079950
time=2024-06-22T18:12:30.701Z level=INFO source=server.go:572 msg="llama runner started in 1.25 seconds"
[GIN] 2024/06/22 - 18:12:30 | 200 |  1.844428132s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2024/06/22 - 18:12:46 | 200 |  7.642005051s |       127.0.0.1 | POST     "/api/chat"
<!-- gh-comment-id:2184138898 --> @praharshbhatt commented on GitHub (Jun 22, 2024): `ollama version is 0.1.40` --- Created the docker using: ```bash sudo docker run -d \ -v ollama:/root/.ollama \ -p 11434:11434 \ -e OLLAMA_ORIGINS="app://obsidian.md*" \ --gpus=all \ --name ollama ollama/ollama ``` --- logs: ``` time=2024-06-22T18:12:29.447Z level=INFO source=server.go:341 msg="starting llama server" cmd="/tmp/ollama1711348412/runners/cpu_avx2/ollama_llama_server --model /root/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 2048 --batch-size 512 --embedding --log-disable --parallel 1 --port 38033" time=2024-06-22T18:12:29.448Z level=INFO source=sched.go:338 msg="loaded runners" count=1 time=2024-06-22T18:12:29.448Z level=INFO source=server.go:529 msg="waiting for llama runner to start responding" time=2024-06-22T18:12:29.448Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server error" INFO [main] build info | build=1 commit="5921b8f" tid="139712474826624" timestamp=1719079949 INFO [main] system info | n_threads=8 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="139712474826624" timestamp=1719079949 total_threads=16 INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="15" port="38033" tid="139712474826624" timestamp=1719079949 llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.name str = Meta-Llama-3-8B-Instruct llama_model_loader: - kv 2: llama.block_count u32 = 32 llama_model_loader: - kv 3: llama.context_length u32 = 8192 llama_model_loader: - kv 4: llama.embedding_length u32 = 4096 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.attention.head_count u32 = 32 llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 8: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: general.file_type u32 = 2 llama_model_loader: - kv 11: llama.vocab_size u32 = 128256 llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 14: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 20: tokenizer.chat_template str = {% set loop_messages = messages %}{% ... llama_model_loader: - kv 21: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_0: 225 tensors llama_model_loader: - type q6_K: 1 tensors time=2024-06-22T18:12:29.698Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 1.5928 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 4 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 14336 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_yarn_orig_ctx = 8192 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: model type = 8B llm_load_print_meta: model ftype = Q4_0 llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 4.33 GiB (4.64 BPW) llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_tensors: ggml ctx size = 0.15 MiB llm_load_tensors: CPU buffer size = 4437.80 MiB llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CPU KV buffer size = 256.00 MiB llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB llama_new_context_with_model: CPU output buffer size = 0.50 MiB llama_new_context_with_model: CPU compute buffer size = 258.50 MiB llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 1 INFO [main] model loaded | tid="139712474826624" timestamp=1719079950 time=2024-06-22T18:12:30.701Z level=INFO source=server.go:572 msg="llama runner started in 1.25 seconds" [GIN] 2024/06/22 - 18:12:30 | 200 | 1.844428132s | 127.0.0.1 | POST "/api/chat" [GIN] 2024/06/22 - 18:12:46 | 200 | 7.642005051s | 127.0.0.1 | POST "/api/chat" ```
GiteaMirror commented 2026-04-12 11:40:43 -05:00
Author
Owner
Copy Link

@praharshbhatt commented on GitHub (Jun 22, 2024):

another update- it seems like right after a restart, everything works well. I think the issue is related to nvidia-modprobe, and not related to ollama.

logs after restart:

llama_model_loader: - kv   0:                       general.architecture str              = llama
llama_model_loader: - kv   1:                               general.name str              = Meta-Llama-3-8B-Instruct
llama_model_loader: - kv   2:                          llama.block_count u32              = 32
llama_model_loader: - kv   3:                       llama.context_length u32              = 8192
llama_model_loader: - kv   4:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv   6:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv   7:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv   8:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  10:                          general.file_type u32              = 2
llama_model_loader: - kv  11:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  12:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 128009
llama_model_loader: - kv  20:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv  21:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q4_0:  225 tensors
llama_model_loader: - type q6_K:    1 tensors
time=2024-06-22T18:30:16.671Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 1.5928 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 128256
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: n_ctx_train      = 8192
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 4
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 14336
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx  = 8192
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: model type       = 8B
llm_load_print_meta: model ftype      = Q4_0
llm_load_print_meta: model params     = 8.03 B
llm_load_print_meta: model size       = 4.33 GiB (4.64 BPW) 
llm_load_print_meta: general.name     = Meta-Llama-3-8B-Instruct
llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:   yes
ggml_cuda_init: CUDA_USE_TENSOR_CORES: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
llm_load_tensors: ggml ctx size =    0.30 MiB
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 33/33 layers to GPU
llm_load_tensors:        CPU buffer size =   281.81 MiB
llm_load_tensors:      CUDA0 buffer size =  4155.99 MiB
llama_new_context_with_model: n_ctx      = 2048
llama_new_context_with_model: n_batch    = 512
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base  = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init:      CUDA0 KV buffer size =   256.00 MiB
llama_new_context_with_model: KV self size  =  256.00 MiB, K (f16):  128.00 MiB, V (f16):  128.00 MiB
llama_new_context_with_model:  CUDA_Host  output buffer size =     0.50 MiB
llama_new_context_with_model:      CUDA0 compute buffer size =   258.50 MiB
llama_new_context_with_model:  CUDA_Host compute buffer size =    12.01 MiB
llama_new_context_with_model: graph nodes  = 1030
llama_new_context_with_model: graph splits = 2
INFO [main] model loaded | tid="139904267825152" timestamp=1719081027
time=2024-06-22T18:30:27.219Z level=INFO source=server.go:572 msg="llama runner started in 10.80 seconds"
[GIN] 2024/06/22 - 18:30:27 | 200 | 11.433096234s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2024/06/22 - 18:30:33 | 200 |  850.682706ms |       127.0.0.1 | POST     "/api/chat"

thank you!

<!-- gh-comment-id:2184148287 --> @praharshbhatt commented on GitHub (Jun 22, 2024): another update- it seems like right after a restart, everything works well. I think the issue is related to nvidia-modprobe, and not related to ollama. logs after restart: ``` llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.name str = Meta-Llama-3-8B-Instruct llama_model_loader: - kv 2: llama.block_count u32 = 32 llama_model_loader: - kv 3: llama.context_length u32 = 8192 llama_model_loader: - kv 4: llama.embedding_length u32 = 4096 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.attention.head_count u32 = 32 llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 8: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: general.file_type u32 = 2 llama_model_loader: - kv 11: llama.vocab_size u32 = 128256 llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 14: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 20: tokenizer.chat_template str = {% set loop_messages = messages %}{% ... llama_model_loader: - kv 21: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_0: 225 tensors llama_model_loader: - type q6_K: 1 tensors time=2024-06-22T18:30:16.671Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 1.5928 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 4 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 14336 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_yarn_orig_ctx = 8192 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: model type = 8B llm_load_print_meta: model ftype = Q4_0 llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 4.33 GiB (4.64 BPW) llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' ggml_cuda_init: GGML_CUDA_FORCE_MMQ: yes ggml_cuda_init: CUDA_USE_TENSOR_CORES: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes llm_load_tensors: ggml ctx size = 0.30 MiB llm_load_tensors: offloading 32 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 33/33 layers to GPU llm_load_tensors: CPU buffer size = 281.81 MiB llm_load_tensors: CUDA0 buffer size = 4155.99 MiB llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA0 KV buffer size = 256.00 MiB llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.50 MiB llama_new_context_with_model: CUDA0 compute buffer size = 258.50 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 12.01 MiB llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 2 INFO [main] model loaded | tid="139904267825152" timestamp=1719081027 time=2024-06-22T18:30:27.219Z level=INFO source=server.go:572 msg="llama runner started in 10.80 seconds" [GIN] 2024/06/22 - 18:30:27 | 200 | 11.433096234s | 127.0.0.1 | POST "/api/chat" [GIN] 2024/06/22 - 18:30:33 | 200 | 850.682706ms | 127.0.0.1 | POST "/api/chat" ``` thank you!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#1701
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?