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 #5816] orian ollama webui #50137

New Issue
Closed
opened 2026-04-28 14:19:20 -05:00 by GiteaMirror · 32 comments
GiteaMirror commented 2026-04-28 14:19:20 -05:00
Owner
Copy Link

Originally created by @werruww on GitHub (Jul 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5816

Failed to post request http://Localhost:11434

(b) C:\Users\m\Desktop\1>ollama serve
Error: listen tcp 127.0.0.1:11434: bind: Only one usage of each socket address (protocol/network address/port) is normally permitted.

ollama not work with add orian ollama webui on egde

Originally created by @werruww on GitHub (Jul 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5816 Failed to post request http://Localhost:11434 (b) C:\Users\m\Desktop\1>ollama serve Error: listen tcp 127.0.0.1:11434: bind: Only one usage of each socket address (protocol/network address/port) is normally permitted. ollama not work with add orian ollama webui on egde
GiteaMirror added the feature request label 2026-04-28 14:19:21 -05:00
GiteaMirror commented 2026-04-28 14:19:30 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 20, 2024):

Either there's already an ollama server running, or something else is using the port. If ollama list fails, then it's likely a different process. You can use netstat -aon | findstr :11434 to find the id of the process that has bound to the port, and then find the name of the program with tasklist /FI "PID eq xxxx", where xxxx is the number at the end of the line from the nestat command.

<!-- gh-comment-id:2241299878 --> @rick-github commented on GitHub (Jul 20, 2024): Either there's already an ollama server running, or something else is using the port. If `ollama list` fails, then it's likely a different process. You can use `netstat -aon | findstr :11434` to find the id of the process that has bound to the port, and then find the name of the program with `tasklist /FI "PID eq xxxx"`, where `xxxx` is the number at the end of the line from the `nestat` command.
GiteaMirror commented 2026-04-28 14:19:33 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 20, 2024):

(b) C:\Users\m\Desktop\1>netstat -aon | findstr :11434
TCP 127.0.0.1:11434 0.0.0.0:0 LISTENING 4184
TCP 127.0.0.1:11434 127.0.0.1:58211 ESTABLISHED 4184
TCP 127.0.0.1:58211 127.0.0.1:11434 ESTABLISHED 2628

<!-- gh-comment-id:2241300878 --> @werruww commented on GitHub (Jul 20, 2024): (b) C:\Users\m\Desktop\1>netstat -aon | findstr :11434 TCP 127.0.0.1:11434 0.0.0.0:0 LISTENING 4184 TCP 127.0.0.1:11434 127.0.0.1:58211 ESTABLISHED 4184 TCP 127.0.0.1:58211 127.0.0.1:11434 ESTABLISHED 2628
GiteaMirror commented 2026-04-28 14:19:36 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 20, 2024):

Now do tasklist /FI "PID eq 4184"

<!-- gh-comment-id:2241312911 --> @rick-github commented on GitHub (Jul 20, 2024): Now do `tasklist /FI "PID eq 4184"`
GiteaMirror commented 2026-04-28 14:19:39 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 21, 2024):

(b) C:\Users\m\Desktop\e>netstat -aon | findstr :11434
TCP 127.0.0.1:11434 0.0.0.0:0 LISTENING 8812
TCP 127.0.0.1:52102 127.0.0.1:11434 TIME_WAIT 0

(b) C:\Users\m\Desktop\e>tasklist /FI "PID eq 4184"
INFO: No tasks are running which match the specified criteria.

<!-- gh-comment-id:2241809235 --> @werruww commented on GitHub (Jul 21, 2024): (b) C:\Users\m\Desktop\e>netstat -aon | findstr :11434 TCP 127.0.0.1:11434 0.0.0.0:0 LISTENING 8812 TCP 127.0.0.1:52102 127.0.0.1:11434 TIME_WAIT 0 (b) C:\Users\m\Desktop\e>tasklist /FI "PID eq 4184" INFO: No tasks are running which match the specified criteria.
GiteaMirror commented 2026-04-28 14:19:45 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 21, 2024):

Untitled

<!-- gh-comment-id:2241809586 --> @werruww commented on GitHub (Jul 21, 2024): ![Untitled](https://github.com/user-attachments/assets/f881f0af-fe07-40fe-8cd0-e71235264aba)
GiteaMirror commented 2026-04-28 14:19:54 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 21, 2024):

Now do tasklist /FI "PID eq 8812"

<!-- gh-comment-id:2241809742 --> @rick-github commented on GitHub (Jul 21, 2024): Now do `tasklist /FI "PID eq 8812"`
GiteaMirror commented 2026-04-28 14:20:02 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 21, 2024):

U2ntitled

<!-- gh-comment-id:2241810001 --> @werruww commented on GitHub (Jul 21, 2024): ![U2ntitled](https://github.com/user-attachments/assets/10f4320a-b170-490a-a3ba-490da3302456)
GiteaMirror commented 2026-04-28 14:20:08 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 21, 2024):

(b) C:\Users\m\Desktop\e>tasklist /FI "PID eq 8812"

Image Name PID Session Name Session# Mem Usage
========================= ======== ================ =========== ============
ollama.exe 8812 Console 1 19,752 K

(b) C:\Users\m\Desktop\e>

<!-- gh-comment-id:2241810026 --> @werruww commented on GitHub (Jul 21, 2024): (b) C:\Users\m\Desktop\e>tasklist /FI "PID eq 8812" Image Name PID Session Name Session# Mem Usage ========================= ======== ================ =========== ============ ollama.exe 8812 Console 1 19,752 K (b) C:\Users\m\Desktop\e>
GiteaMirror commented 2026-04-28 14:20:13 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 21, 2024):

From the screenshot, orian was able to retrieve the model list, so it can communicate with the ollama server. What do the ollama server logs show when you ask a question and it fails?

<!-- gh-comment-id:2241811583 --> @rick-github commented on GitHub (Jul 21, 2024): From the screenshot, orian was able to retrieve the model list, so it can communicate with the ollama server. What do the ollama server logs show when you ask a question and it fails?
GiteaMirror commented 2026-04-28 14:20:14 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 21, 2024):

2024/07/21 15:39:59 routes.go:1064: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE: OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:C:\Users\m\.ollama\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\Users\m\AppData\Local\Programs\Ollama\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-07-21T15:39:59.249-07:00 level=INFO source=images.go:730 msg="total blobs: 4"
time=2024-07-21T15:39:59.250-07:00 level=INFO source=images.go:737 msg="total unused blobs removed: 0"
time=2024-07-21T15:39:59.250-07:00 level=INFO source=routes.go:1111 msg="Listening on 127.0.0.1:11434 (version 0.1.46)"
time=2024-07-21T15:39:59.251-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11.3 rocm_v5.7]"
time=2024-07-21T15:39:59.274-07:00 level=INFO source=types.go:98 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="16.0 GiB" available="12.2 GiB"
[GIN] 2024/07/21 - 15:39:59 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2024/07/21 - 15:39:59 | 200 | 4.745ms | 127.0.0.1 | GET "/api/tags"

<!-- gh-comment-id:2241817358 --> @werruww commented on GitHub (Jul 21, 2024): 2024/07/21 15:39:59 routes.go:1064: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE: OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:C:\\Users\\m\\.ollama\\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\\Users\\m\\AppData\\Local\\Programs\\Ollama\\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-07-21T15:39:59.249-07:00 level=INFO source=images.go:730 msg="total blobs: 4" time=2024-07-21T15:39:59.250-07:00 level=INFO source=images.go:737 msg="total unused blobs removed: 0" time=2024-07-21T15:39:59.250-07:00 level=INFO source=routes.go:1111 msg="Listening on 127.0.0.1:11434 (version 0.1.46)" time=2024-07-21T15:39:59.251-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11.3 rocm_v5.7]" time=2024-07-21T15:39:59.274-07:00 level=INFO source=types.go:98 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="16.0 GiB" available="12.2 GiB" [GIN] 2024/07/21 - 15:39:59 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2024/07/21 - 15:39:59 | 200 | 4.745ms | 127.0.0.1 | GET "/api/tags"
GiteaMirror commented 2026-04-28 14:20:16 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 21, 2024):

2024/07/21 15:40:57 routes.go:1096: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:C:\Users\m\.ollama\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\Users\m\AppData\Local\Programs\Ollama\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-07-21T15:40:57.045-07:00 level=INFO source=images.go:778 msg="total blobs: 4"
time=2024-07-21T15:40:57.046-07:00 level=INFO source=images.go:785 msg="total unused blobs removed: 0"
time=2024-07-21T15:40:57.047-07:00 level=INFO source=routes.go:1143 msg="Listening on 127.0.0.1:11434 (version 0.2.7)"
time=2024-07-21T15:40:57.048-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [rocm_v6.1 cpu cpu_avx cpu_avx2 cuda_v11.3]"
time=2024-07-21T15:40:57.048-07:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs"
time=2024-07-21T15:40:57.068-07:00 level=INFO source=gpu.go:346 msg="no compatible GPUs were discovered"
time=2024-07-21T15:40:57.068-07:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="16.0 GiB" available="11.6 GiB"
[GIN] 2024/07/21 - 15:40:57 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2024/07/21 - 15:40:57 | 200 | 5.025ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 15:41:01 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2024/07/21 - 15:41:16 | 200 | 2.0518ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 15:41:17 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 15:41:46 | 403 | 0s | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 15:41:52 | 403 | 0s | 127.0.0.1 | OPTIONS "/api/generate"
[GIN] 2024/07/21 - 15:42:39 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2024/07/21 - 15:42:39 | 200 | 23.9883ms | 127.0.0.1 | POST "/api/show"
time=2024-07-21T15:42:39.983-07:00 level=INFO source=memory.go:309 msg="offload to cpu" layers.requested=-1 layers.model=33 layers.offload=0 layers.split="" memory.available="[12.4 GiB]" memory.required.full="5.2 GiB" memory.required.partial="0 B" memory.required.kv="512.0 MiB" memory.required.allocations="[5.2 GiB]" memory.weights.total="4.4 GiB" memory.weights.repeating="4.0 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="296.0 MiB" memory.graph.partial="677.5 MiB"
time=2024-07-21T15:42:39.993-07:00 level=INFO source=server.go:383 msg="starting llama server" cmd="C:\Users\m\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx2\ollama_llama_server.exe --model C:\Users\m\.ollama\models\blobs\sha256-ab9e4eec7e80892fd78f74d9a15d0299f1e22121cea44efd68a7a02a3fe9a1da --ctx-size 4096 --batch-size 512 --embedding --log-disable --no-mmap --parallel 4 --port 51080"
time=2024-07-21T15:42:40.037-07:00 level=INFO source=sched.go:437 msg="loaded runners" count=1
time=2024-07-21T15:42:40.037-07:00 level=INFO source=server.go:571 msg="waiting for llama runner to start responding"
time=2024-07-21T15:42:40.037-07:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server error"
INFO [wmain] build info | build=3337 commit="a8db2a9c" tid="5964" timestamp=1721601760
INFO [wmain] system info | n_threads=4 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 = 0 | " tid="5964" timestamp=1721601760 total_threads=4
INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="6" port="51080" tid="5964" timestamp=1721601760
llama_model_loader: loaded meta data with 21 key-value pairs and 291 tensors from C:\Users\m.ollama\models\blobs\sha256-ab9e4eec7e80892fd78f74d9a15d0299f1e22121cea44efd68a7a02a3fe9a1da (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-imatrix
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 = 15
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.tokens arr[str,128256] = ["!", """, "#", "$", "%", "&", "'", ...
time=2024-07-21T15:42:40.290-07:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server loading model"
llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 16: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 128001
llama_model_loader: - kv 19: tokenizer.chat_template str = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv 20: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default'
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.8000 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: vocab_only = 0
llm_load_print_meta: n_ctx_train = 8192
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_swa = 0
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_ctx_orig_yarn = 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_K - Medium
llm_load_print_meta: model params = 8.03 B
llm_load_print_meta: model size = 4.58 GiB (4.89 BPW)
llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct-imatrix
llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token = 128001 '<|end_of_text|>'
llm_load_print_meta: LF token = 128 'Ä'
llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: ggml ctx size = 0.14 MiB
llm_load_tensors: CPU buffer size = 4685.30 MiB
[GIN] 2024/07/21 - 15:42:52 | 403 | 0s | 127.0.0.1 | GET "/api/tags"
llama_new_context_with_model: n_ctx = 4096
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 = 512.00 MiB
llama_new_context_with_model: KV self size = 512.00 MiB, K (f16): 256.00 MiB, V (f16): 256.00 MiB
llama_new_context_with_model: CPU output buffer size = 2.02 MiB
llama_new_context_with_model: CPU compute buffer size = 296.01 MiB
llama_new_context_with_model: graph nodes = 1030
llama_new_context_with_model: graph splits = 1
INFO [wmain] model loaded | tid="5964" timestamp=1721601842
time=2024-07-21T15:44:02.055-07:00 level=INFO source=server.go:617 msg="llama runner started in 82.02 seconds"
[GIN] 2024/07/21 - 15:44:02 | 200 | 1m22s | 127.0.0.1 | POST "/api/chat"
[GIN] 2024/07/21 - 15:44:07 | 403 | 0s | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 15:44:39 | 200 | 997.9µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 15:44:41 | 200 | 22.664353s | 127.0.0.1 | POST "/api/chat"
[GIN] 2024/07/21 - 15:44:43 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 15:50:27 | 200 | 1.5728ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 15:50:28 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 15:50:48 | 200 | 1.4457ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 15:50:51 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 15:52:10 | 200 | 6.7769ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 15:52:13 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 15:52:40 | 200 | 6.2826ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 15:52:51 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 15:53:00 | 200 | 2.1904ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 15:53:02 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 15:53:36 | 200 | 1.0021ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 15:54:15 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
time=2024-07-21T16:05:17.322-07:00 level=INFO source=memory.go:309 msg="offload to cpu" layers.requested=-1 layers.model=33 layers.offload=0 layers.split="" memory.available="[12.0 GiB]" memory.required.full="5.2 GiB" memory.required.partial="0 B" memory.required.kv="512.0 MiB" memory.required.allocations="[5.2 GiB]" memory.weights.total="4.4 GiB" memory.weights.repeating="4.0 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="296.0 MiB" memory.graph.partial="677.5 MiB"
time=2024-07-21T16:05:17.327-07:00 level=INFO source=server.go:383 msg="starting llama server" cmd="C:\Users\m\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx2\ollama_llama_server.exe --model C:\Users\m\.ollama\models\blobs\sha256-ab9e4eec7e80892fd78f74d9a15d0299f1e22121cea44efd68a7a02a3fe9a1da --ctx-size 4096 --batch-size 512 --embedding --log-disable --no-mmap --parallel 4 --port 51486"
time=2024-07-21T16:05:17.331-07:00 level=INFO source=sched.go:437 msg="loaded runners" count=1
time=2024-07-21T16:05:17.331-07:00 level=INFO source=server.go:571 msg="waiting for llama runner to start responding"
time=2024-07-21T16:05:17.331-07:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server error"
INFO [wmain] build info | build=3337 commit="a8db2a9c" tid="2840" timestamp=1721603117
INFO [wmain] system info | n_threads=4 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 = 0 | " tid="2840" timestamp=1721603117 total_threads=4
INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="6" port="51486" tid="2840" timestamp=1721603117
llama_model_loader: loaded meta data with 21 key-value pairs and 291 tensors from C:\Users\m.ollama\models\blobs\sha256-ab9e4eec7e80892fd78f74d9a15d0299f1e22121cea44efd68a7a02a3fe9a1da (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-imatrix
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 = 15
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.tokens arr[str,128256] = ["!", """, "#", "$", "%", "&", "'", ...
time=2024-07-21T16:05:17.586-07:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server loading model"
llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 16: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 128001
llama_model_loader: - kv 19: tokenizer.chat_template str = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv 20: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default'
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.8000 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: vocab_only = 0
llm_load_print_meta: n_ctx_train = 8192
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_swa = 0
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_ctx_orig_yarn = 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_K - Medium
llm_load_print_meta: model params = 8.03 B
llm_load_print_meta: model size = 4.58 GiB (4.89 BPW)
llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct-imatrix
llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token = 128001 '<|end_of_text|>'
llm_load_print_meta: LF token = 128 'Ä'
llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: ggml ctx size = 0.14 MiB
llm_load_tensors: CPU buffer size = 4685.30 MiB
llama_new_context_with_model: n_ctx = 4096
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 = 512.00 MiB
llama_new_context_with_model: KV self size = 512.00 MiB, K (f16): 256.00 MiB, V (f16): 256.00 MiB
llama_new_context_with_model: CPU output buffer size = 2.02 MiB
llama_new_context_with_model: CPU compute buffer size = 296.01 MiB
llama_new_context_with_model: graph nodes = 1030
llama_new_context_with_model: graph splits = 1
INFO [wmain] model loaded | tid="2840" timestamp=1721603122
time=2024-07-21T16:05:22.777-07:00 level=INFO source=server.go:617 msg="llama runner started in 5.45 seconds"
[GIN] 2024/07/21 - 16:05:36 | 200 | 19.6263103s | 127.0.0.1 | POST "/api/chat"
[GIN] 2024/07/21 - 16:09:01 | 200 | 1.0746ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 16:09:02 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 16:09:34 | 200 | 10.0524ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 16:09:35 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 16:16:46 | 200 | 1.3193ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 16:16:48 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 16:17:01 | 200 | 3.3784ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 16:17:06 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 16:19:40 | 200 | 2.1921ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 16:19:41 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 16:22:18 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/07/21 - 16:42:30 | 200 | 1.619ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/07/21 - 16:42:32 | 403 | 0s | 127.0.0.1 | POST "/api/generate"

<!-- gh-comment-id:2241817592 --> @werruww commented on GitHub (Jul 21, 2024): 2024/07/21 15:40:57 routes.go:1096: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:C:\\Users\\m\\.ollama\\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\\Users\\m\\AppData\\Local\\Programs\\Ollama\\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-07-21T15:40:57.045-07:00 level=INFO source=images.go:778 msg="total blobs: 4" time=2024-07-21T15:40:57.046-07:00 level=INFO source=images.go:785 msg="total unused blobs removed: 0" time=2024-07-21T15:40:57.047-07:00 level=INFO source=routes.go:1143 msg="Listening on 127.0.0.1:11434 (version 0.2.7)" time=2024-07-21T15:40:57.048-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [rocm_v6.1 cpu cpu_avx cpu_avx2 cuda_v11.3]" time=2024-07-21T15:40:57.048-07:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs" time=2024-07-21T15:40:57.068-07:00 level=INFO source=gpu.go:346 msg="no compatible GPUs were discovered" time=2024-07-21T15:40:57.068-07:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="16.0 GiB" available="11.6 GiB" [GIN] 2024/07/21 - 15:40:57 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2024/07/21 - 15:40:57 | 200 | 5.025ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 15:41:01 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2024/07/21 - 15:41:16 | 200 | 2.0518ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 15:41:17 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 15:41:46 | 403 | 0s | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 15:41:52 | 403 | 0s | 127.0.0.1 | OPTIONS "/api/generate" [GIN] 2024/07/21 - 15:42:39 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2024/07/21 - 15:42:39 | 200 | 23.9883ms | 127.0.0.1 | POST "/api/show" time=2024-07-21T15:42:39.983-07:00 level=INFO source=memory.go:309 msg="offload to cpu" layers.requested=-1 layers.model=33 layers.offload=0 layers.split="" memory.available="[12.4 GiB]" memory.required.full="5.2 GiB" memory.required.partial="0 B" memory.required.kv="512.0 MiB" memory.required.allocations="[5.2 GiB]" memory.weights.total="4.4 GiB" memory.weights.repeating="4.0 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="296.0 MiB" memory.graph.partial="677.5 MiB" time=2024-07-21T15:42:39.993-07:00 level=INFO source=server.go:383 msg="starting llama server" cmd="C:\\Users\\m\\AppData\\Local\\Programs\\Ollama\\ollama_runners\\cpu_avx2\\ollama_llama_server.exe --model C:\\Users\\m\\.ollama\\models\\blobs\\sha256-ab9e4eec7e80892fd78f74d9a15d0299f1e22121cea44efd68a7a02a3fe9a1da --ctx-size 4096 --batch-size 512 --embedding --log-disable --no-mmap --parallel 4 --port 51080" time=2024-07-21T15:42:40.037-07:00 level=INFO source=sched.go:437 msg="loaded runners" count=1 time=2024-07-21T15:42:40.037-07:00 level=INFO source=server.go:571 msg="waiting for llama runner to start responding" time=2024-07-21T15:42:40.037-07:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server error" INFO [wmain] build info | build=3337 commit="a8db2a9c" tid="5964" timestamp=1721601760 INFO [wmain] system info | n_threads=4 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 = 0 | " tid="5964" timestamp=1721601760 total_threads=4 INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="6" port="51080" tid="5964" timestamp=1721601760 llama_model_loader: loaded meta data with 21 key-value pairs and 291 tensors from C:\Users\m\.ollama\models\blobs\sha256-ab9e4eec7e80892fd78f74d9a15d0299f1e22121cea44efd68a7a02a3fe9a1da (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-imatrix 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 = 15 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.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... time=2024-07-21T15:42:40.290-07:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 16: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 128001 llama_model_loader: - kv 19: tokenizer.chat_template str = {% set loop_messages = messages %}{% ... llama_model_loader: - kv 20: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_K: 193 tensors llama_model_loader: - type q6_K: 33 tensors llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default' llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.8000 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: vocab_only = 0 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 0 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_ctx_orig_yarn = 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_K - Medium llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 4.58 GiB (4.89 BPW) llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct-imatrix llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128001 '<|end_of_text|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 llm_load_tensors: ggml ctx size = 0.14 MiB llm_load_tensors: CPU buffer size = 4685.30 MiB [GIN] 2024/07/21 - 15:42:52 | 403 | 0s | 127.0.0.1 | GET "/api/tags" llama_new_context_with_model: n_ctx = 4096 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 = 512.00 MiB llama_new_context_with_model: KV self size = 512.00 MiB, K (f16): 256.00 MiB, V (f16): 256.00 MiB llama_new_context_with_model: CPU output buffer size = 2.02 MiB llama_new_context_with_model: CPU compute buffer size = 296.01 MiB llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 1 INFO [wmain] model loaded | tid="5964" timestamp=1721601842 time=2024-07-21T15:44:02.055-07:00 level=INFO source=server.go:617 msg="llama runner started in 82.02 seconds" [GIN] 2024/07/21 - 15:44:02 | 200 | 1m22s | 127.0.0.1 | POST "/api/chat" [GIN] 2024/07/21 - 15:44:07 | 403 | 0s | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 15:44:39 | 200 | 997.9µs | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 15:44:41 | 200 | 22.664353s | 127.0.0.1 | POST "/api/chat" [GIN] 2024/07/21 - 15:44:43 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 15:50:27 | 200 | 1.5728ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 15:50:28 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 15:50:48 | 200 | 1.4457ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 15:50:51 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 15:52:10 | 200 | 6.7769ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 15:52:13 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 15:52:40 | 200 | 6.2826ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 15:52:51 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 15:53:00 | 200 | 2.1904ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 15:53:02 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 15:53:36 | 200 | 1.0021ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 15:54:15 | 403 | 0s | 127.0.0.1 | POST "/api/generate" time=2024-07-21T16:05:17.322-07:00 level=INFO source=memory.go:309 msg="offload to cpu" layers.requested=-1 layers.model=33 layers.offload=0 layers.split="" memory.available="[12.0 GiB]" memory.required.full="5.2 GiB" memory.required.partial="0 B" memory.required.kv="512.0 MiB" memory.required.allocations="[5.2 GiB]" memory.weights.total="4.4 GiB" memory.weights.repeating="4.0 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="296.0 MiB" memory.graph.partial="677.5 MiB" time=2024-07-21T16:05:17.327-07:00 level=INFO source=server.go:383 msg="starting llama server" cmd="C:\\Users\\m\\AppData\\Local\\Programs\\Ollama\\ollama_runners\\cpu_avx2\\ollama_llama_server.exe --model C:\\Users\\m\\.ollama\\models\\blobs\\sha256-ab9e4eec7e80892fd78f74d9a15d0299f1e22121cea44efd68a7a02a3fe9a1da --ctx-size 4096 --batch-size 512 --embedding --log-disable --no-mmap --parallel 4 --port 51486" time=2024-07-21T16:05:17.331-07:00 level=INFO source=sched.go:437 msg="loaded runners" count=1 time=2024-07-21T16:05:17.331-07:00 level=INFO source=server.go:571 msg="waiting for llama runner to start responding" time=2024-07-21T16:05:17.331-07:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server error" INFO [wmain] build info | build=3337 commit="a8db2a9c" tid="2840" timestamp=1721603117 INFO [wmain] system info | n_threads=4 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 = 0 | " tid="2840" timestamp=1721603117 total_threads=4 INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="6" port="51486" tid="2840" timestamp=1721603117 llama_model_loader: loaded meta data with 21 key-value pairs and 291 tensors from C:\Users\m\.ollama\models\blobs\sha256-ab9e4eec7e80892fd78f74d9a15d0299f1e22121cea44efd68a7a02a3fe9a1da (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-imatrix 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 = 15 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.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... time=2024-07-21T16:05:17.586-07:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 16: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 128001 llama_model_loader: - kv 19: tokenizer.chat_template str = {% set loop_messages = messages %}{% ... llama_model_loader: - kv 20: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_K: 193 tensors llama_model_loader: - type q6_K: 33 tensors llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default' llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.8000 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: vocab_only = 0 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 0 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_ctx_orig_yarn = 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_K - Medium llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 4.58 GiB (4.89 BPW) llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct-imatrix llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128001 '<|end_of_text|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 llm_load_tensors: ggml ctx size = 0.14 MiB llm_load_tensors: CPU buffer size = 4685.30 MiB llama_new_context_with_model: n_ctx = 4096 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 = 512.00 MiB llama_new_context_with_model: KV self size = 512.00 MiB, K (f16): 256.00 MiB, V (f16): 256.00 MiB llama_new_context_with_model: CPU output buffer size = 2.02 MiB llama_new_context_with_model: CPU compute buffer size = 296.01 MiB llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 1 INFO [wmain] model loaded | tid="2840" timestamp=1721603122 time=2024-07-21T16:05:22.777-07:00 level=INFO source=server.go:617 msg="llama runner started in 5.45 seconds" [GIN] 2024/07/21 - 16:05:36 | 200 | 19.6263103s | 127.0.0.1 | POST "/api/chat" [GIN] 2024/07/21 - 16:09:01 | 200 | 1.0746ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 16:09:02 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 16:09:34 | 200 | 10.0524ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 16:09:35 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 16:16:46 | 200 | 1.3193ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 16:16:48 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 16:17:01 | 200 | 3.3784ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 16:17:06 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 16:19:40 | 200 | 2.1921ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 16:19:41 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 16:22:18 | 403 | 0s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/07/21 - 16:42:30 | 200 | 1.619ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/21 - 16:42:32 | 403 | 0s | 127.0.0.1 | POST "/api/generate"
GiteaMirror commented 2026-04-28 14:20:17 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 21, 2024):

I used several add-ons for Olama and they worked efficiently, except for this add-on
Un3titled

<!-- gh-comment-id:2241820539 --> @werruww commented on GitHub (Jul 21, 2024): I used several add-ons for Olama and they worked efficiently, except for this add-on ![Un3titled](https://github.com/user-attachments/assets/afc0b36c-2b25-4fec-9b20-51513c731260)
GiteaMirror commented 2026-04-28 14:20:17 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

Untit4led

<!-- gh-comment-id:2241823406 --> @werruww commented on GitHub (Jul 22, 2024): ![Untit4led](https://github.com/user-attachments/assets/7a5e4800-1c6f-47a3-b7b1-85f2757b219c)
GiteaMirror commented 2026-04-28 14:20:19 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

not work

<!-- gh-comment-id:2241823534 --> @werruww commented on GitHub (Jul 22, 2024): not work
GiteaMirror commented 2026-04-28 14:20:20 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 22, 2024):

This is a guess, but I think the capital "L" in Localhost is the problem. ollama has a list of allowed origins (see OLLAMA_ORIGINS in the logs) and it contains localhost but not Localhost. There are two ways to test this: either change the connection string in orian to localhost:11434, or add Localhost to the environment variable OLLAMA_ORIGINS and restart ollama: OLLAMA_ORIGINS=Localhost.

<!-- gh-comment-id:2241824520 --> @rick-github commented on GitHub (Jul 22, 2024): This is a guess, but I think the capital "L" in Localhost is the problem. ollama has a list of allowed origins (see `OLLAMA_ORIGINS` in the logs) and it contains `localhost` but not `Localhost`. There are two ways to test this: either change the connection string in orian to `localhost:11434`, or add `Localhost` to the environment variable `OLLAMA_ORIGINS` and restart ollama: `OLLAMA_ORIGINS=Localhost`.
GiteaMirror commented 2026-04-28 14:20:21 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

(b) C:\Users\m\Desktop\e>set OLLAMA_ORIGINS=http://localhost:11434

(b) C:\Users\m\Desktop\e>

<!-- gh-comment-id:2241826371 --> @werruww commented on GitHub (Jul 22, 2024): (b) C:\Users\m\Desktop\e>set OLLAMA_ORIGINS=http://localhost:11434 (b) C:\Users\m\Desktop\e>
GiteaMirror commented 2026-04-28 14:20:21 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

(b) C:\Users\m\Desktop\e>set OLLAMA_ORIGINS=http://localhost:11434

(b) C:\Users\m\Desktop\e>ollama start
2024/07/21 17:05:35 routes.go:1096: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:C:\Users\m\.ollama\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost:11434 http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\Users\m\AppData\Local\Programs\Ollama\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-07-21T17:05:35.244-07:00 level=INFO source=images.go:778 msg="total blobs: 4"
time=2024-07-21T17:05:35.245-07:00 level=INFO source=images.go:785 msg="total unused blobs removed: 0"
time=2024-07-21T17:05:35.247-07:00 level=INFO source=routes.go:1143 msg="Listening on 127.0.0.1:11434 (version 0.2.7)"
time=2024-07-21T17:05:35.250-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11.3 rocm_v6.1]"
time=2024-07-21T17:05:35.250-07:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs"
time=2024-07-21T17:05:35.329-07:00 level=INFO source=gpu.go:346 msg="no compatible GPUs were discovered"
time=2024-07-21T17:05:35.329-07:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="16.0 GiB" available="9.3 GiB"

(b) C:\Users\m\Desktop\e>

(b) C:\Users\m\Desktop\e>ollama serve
2024/07/21 17:05:53 routes.go:1096: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:C:\Users\m\.ollama\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost:11434 http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\Users\m\AppData\Local\Programs\Ollama\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-07-21T17:05:53.378-07:00 level=INFO source=images.go:778 msg="total blobs: 4"
time=2024-07-21T17:05:53.379-07:00 level=INFO source=images.go:785 msg="total unused blobs removed: 0"
time=2024-07-21T17:05:53.383-07:00 level=INFO source=routes.go:1143 msg="Listening on 127.0.0.1:11434 (version 0.2.7)"
time=2024-07-21T17:05:53.385-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu_avx cpu_avx2 cuda_v11.3 rocm_v6.1 cpu]"
time=2024-07-21T17:05:53.388-07:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs"
time=2024-07-21T17:05:53.410-07:00 level=INFO source=gpu.go:346 msg="no compatible GPUs were discovered"
time=2024-07-21T17:05:53.410-07:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="16.0 GiB" available="9.4 GiB"

(b) C:\Users\m\Desktop\e>ollama list
NAME ID SIZE MODIFIED
Llama-3.gguf:latest 99059b18f23c 4.9 GB 3 hours ago

(b) C:\Users\m\Desktop\e>

<!-- gh-comment-id:2241826418 --> @werruww commented on GitHub (Jul 22, 2024): (b) C:\Users\m\Desktop\e>set OLLAMA_ORIGINS=http://localhost:11434 (b) C:\Users\m\Desktop\e>ollama start 2024/07/21 17:05:35 routes.go:1096: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:C:\\Users\\m\\.ollama\\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost:11434 http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\\Users\\m\\AppData\\Local\\Programs\\Ollama\\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-07-21T17:05:35.244-07:00 level=INFO source=images.go:778 msg="total blobs: 4" time=2024-07-21T17:05:35.245-07:00 level=INFO source=images.go:785 msg="total unused blobs removed: 0" time=2024-07-21T17:05:35.247-07:00 level=INFO source=routes.go:1143 msg="Listening on 127.0.0.1:11434 (version 0.2.7)" time=2024-07-21T17:05:35.250-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11.3 rocm_v6.1]" time=2024-07-21T17:05:35.250-07:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs" time=2024-07-21T17:05:35.329-07:00 level=INFO source=gpu.go:346 msg="no compatible GPUs were discovered" time=2024-07-21T17:05:35.329-07:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="16.0 GiB" available="9.3 GiB" (b) C:\Users\m\Desktop\e> (b) C:\Users\m\Desktop\e>ollama serve 2024/07/21 17:05:53 routes.go:1096: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:C:\\Users\\m\\.ollama\\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost:11434 http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\\Users\\m\\AppData\\Local\\Programs\\Ollama\\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-07-21T17:05:53.378-07:00 level=INFO source=images.go:778 msg="total blobs: 4" time=2024-07-21T17:05:53.379-07:00 level=INFO source=images.go:785 msg="total unused blobs removed: 0" time=2024-07-21T17:05:53.383-07:00 level=INFO source=routes.go:1143 msg="Listening on 127.0.0.1:11434 (version 0.2.7)" time=2024-07-21T17:05:53.385-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu_avx cpu_avx2 cuda_v11.3 rocm_v6.1 cpu]" time=2024-07-21T17:05:53.388-07:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs" time=2024-07-21T17:05:53.410-07:00 level=INFO source=gpu.go:346 msg="no compatible GPUs were discovered" time=2024-07-21T17:05:53.410-07:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="16.0 GiB" available="9.4 GiB" (b) C:\Users\m\Desktop\e>ollama list NAME ID SIZE MODIFIED Llama-3.gguf:latest 99059b18f23c 4.9 GB 3 hours ago (b) C:\Users\m\Desktop\e>
GiteaMirror commented 2026-04-28 14:20:22 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

2024/07/21 15:39:59 routes.go:1064: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE: OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:C:\Users\m\.ollama\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\Users\m\AppData\Local\Programs\Ollama\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-07-21T15:39:59.249-07:00 level=INFO source=images.go:730 msg="total blobs: 4"
time=2024-07-21T15:39:59.250-07:00 level=INFO source=images.go:737 msg="total unused blobs removed: 0"
time=2024-07-21T15:39:59.250-07:00 level=INFO source=routes.go:1111 msg="Listening on 127.0.0.1:11434 (version 0.1.46)"
time=2024-07-21T15:39:59.251-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11.3 rocm_v5.7]"
time=2024-07-21T15:39:59.274-07:00 level=INFO source=types.go:98 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="16.0 GiB" available="12.2 GiB"
[GIN] 2024/07/21 - 15:39:59 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2024/07/21 - 15:39:59 | 200 | 4.745ms | 127.0.0.1 | GET "/api/tags"

<!-- gh-comment-id:2241827229 --> @werruww commented on GitHub (Jul 22, 2024): 2024/07/21 15:39:59 routes.go:1064: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE: OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:C:\\Users\\m\\.ollama\\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\\Users\\m\\AppData\\Local\\Programs\\Ollama\\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-07-21T15:39:59.249-07:00 level=INFO source=images.go:730 msg="total blobs: 4" time=2024-07-21T15:39:59.250-07:00 level=INFO source=images.go:737 msg="total unused blobs removed: 0" time=2024-07-21T15:39:59.250-07:00 level=INFO source=routes.go:1111 msg="Listening on 127.0.0.1:11434 (version 0.1.46)" time=2024-07-21T15:39:59.251-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11.3 rocm_v5.7]" time=2024-07-21T15:39:59.274-07:00 level=INFO source=types.go:98 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="16.0 GiB" available="12.2 GiB" [GIN] 2024/07/21 - 15:39:59 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2024/07/21 - 15:39:59 | 200 | 4.745ms | 127.0.0.1 | GET "/api/tags"
GiteaMirror commented 2026-04-28 14:20:23 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 22, 2024):

OLLAMA_ORIGINS=Localhost

No http prefix.
No port suffix.
Capital "L".
Set it in the process context of the server. I don't know how you do that in windows, but since the logs don't show a change in OLLAMA_ORIGINS, whatever you are doing is not the right way.

<!-- gh-comment-id:2241832377 --> @rick-github commented on GitHub (Jul 22, 2024): `OLLAMA_ORIGINS=Localhost` No http prefix. No port suffix. Capital "L". Set it in the process context of the server. I don't know how you do that in windows, but since the logs don't show a change in `OLLAMA_ORIGINS`, whatever you are doing is not the right way.
GiteaMirror commented 2026-04-28 14:20:24 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

(base) C:\Windows\system32>cd C:\Users\m\Desktop\e\ollama-webui

(base) C:\Users\m\Desktop\e\ollama-webui>conda activate b

(b) C:\Users\m\Desktop\e\ollama-webui>OLLAMA_ORIGINS=Localhost
'OLLAMA_ORIGINS' is not recognized as an internal or external command,
operable program or batch file.

(b) C:\Users\m\Desktop\e\ollama-webui>OLLAMA_ORIGINS=Localhost:11434
'OLLAMA_ORIGINS' is not recognized as an internal or external command,
operable program or batch file.

(b) C:\Users\m\Desktop\e\ollama-webui>OLLAMA_ORIGINS
'OLLAMA_ORIGINS' is not recognized as an internal or external command,
operable program or batch file.

(b) C:\Users\m\Desktop\e\ollama-webui>

<!-- gh-comment-id:2241834940 --> @werruww commented on GitHub (Jul 22, 2024): (base) C:\Windows\system32>cd C:\Users\m\Desktop\e\ollama-webui (base) C:\Users\m\Desktop\e\ollama-webui>conda activate b (b) C:\Users\m\Desktop\e\ollama-webui>OLLAMA_ORIGINS=Localhost 'OLLAMA_ORIGINS' is not recognized as an internal or external command, operable program or batch file. (b) C:\Users\m\Desktop\e\ollama-webui>OLLAMA_ORIGINS=Localhost:11434 'OLLAMA_ORIGINS' is not recognized as an internal or external command, operable program or batch file. (b) C:\Users\m\Desktop\e\ollama-webui>OLLAMA_ORIGINS 'OLLAMA_ORIGINS' is not recognized as an internal or external command, operable program or batch file. (b) C:\Users\m\Desktop\e\ollama-webui>
GiteaMirror commented 2026-04-28 14:20:25 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

Is there an add-on for the browser that works as a mother and has a chat with books?

<!-- gh-comment-id:2241837465 --> @werruww commented on GitHub (Jul 22, 2024): Is there an add-on for the browser that works as a mother and has a chat with books?
GiteaMirror commented 2026-04-28 14:20:27 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 22, 2024):

I don't have specific knowledge of add-ons, but a few are listed in the extensions and plugins section.

<!-- gh-comment-id:2241840355 --> @rick-github commented on GitHub (Jul 22, 2024): I don't have specific knowledge of add-ons, but a few are listed in the [extensions and plugins](https://github.com/ollama/ollama#extensions--plugins) section.
GiteaMirror commented 2026-04-28 14:20:30 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 22, 2024):

This is a bug in the CORS package that ollama uses.

<!-- gh-comment-id:2241917165 --> @rick-github commented on GitHub (Jul 22, 2024): This is a bug in the CORS package that ollama uses.
GiteaMirror commented 2026-04-28 14:20:33 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

Olama's add-ons work with chat, but the add-ons that have chat with books are the ones that do not work

<!-- gh-comment-id:2241922791 --> @werruww commented on GitHub (Jul 22, 2024): Olama's add-ons work with chat, but the add-ons that have chat with books are the ones that do not work
GiteaMirror commented 2026-04-28 14:20:36 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

What is the solution؟

<!-- gh-comment-id:2241927090 --> @werruww commented on GitHub (Jul 22, 2024): What is the solution؟
GiteaMirror commented 2026-04-28 14:20:37 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 22, 2024):

Two possible solutions. 1) file a bug with the developer of orian and ask them to lowercase the hostname. 2) file a bug with the developer of github.com/gin-contrib/cors and ask them to do case-insensitive checking of the hostname. I couldn't find a github repo for orian, so number 2 is probably easier. But that may take a while, it would be faster for the developer of orian to fix their code.

<!-- gh-comment-id:2241929995 --> @rick-github commented on GitHub (Jul 22, 2024): Two possible solutions. 1) file a bug with the developer of orian and ask them to lowercase the hostname. 2) file a bug with the developer of `github.com/gin-contrib/cors` and ask them to do case-insensitive checking of the hostname. I couldn't find a github repo for orian, so number 2 is probably easier. But that may take a while, it would be faster for the developer of orian to fix their code.
GiteaMirror commented 2026-04-28 14:20:37 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

I want a Python script to create a chat with a book using Obama in the terminal

<!-- gh-comment-id:2241932559 --> @werruww commented on GitHub (Jul 22, 2024): I want a Python script to create a chat with a book using Obama in the terminal
GiteaMirror commented 2026-04-28 14:20:38 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

or add for edge

<!-- gh-comment-id:2241932827 --> @werruww commented on GitHub (Jul 22, 2024): or add for edge
GiteaMirror commented 2026-04-28 14:20:39 -05:00
Author
Owner
Copy Link

@werruww commented on GitHub (Jul 22, 2024):

and thank you

<!-- gh-comment-id:2241933040 --> @werruww commented on GitHub (Jul 22, 2024): and thank you
GiteaMirror commented 2026-04-28 14:20:40 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 22, 2024):

there are plenty of terminal demos that you can modify, eg https://github.com/steinbring/python-langchain-rag-demo or https://docs.llamaindex.ai/en/stable/getting_started/starter_tools/rag_cli/. If you are looking for something more complete but runs in the browser instead of terminal, look at https://github.com/datvodinh/rag-chatbot.git or https://github.com/infiniflow/ragflow.

There are more listed on the ollama integrations page, https://github.com/ollama/ollama?tab=readme-ov-file#community-integrations

<!-- gh-comment-id:2241944831 --> @rick-github commented on GitHub (Jul 22, 2024): there are plenty of terminal demos that you can modify, eg https://github.com/steinbring/python-langchain-rag-demo or https://docs.llamaindex.ai/en/stable/getting_started/starter_tools/rag_cli/. If you are looking for something more complete but runs in the browser instead of terminal, look at https://github.com/datvodinh/rag-chatbot.git or https://github.com/infiniflow/ragflow. There are more listed on the ollama integrations page, https://github.com/ollama/ollama?tab=readme-ov-file#community-integrations
GiteaMirror commented 2026-04-28 14:20:40 -05:00
Author
Owner
Copy Link

@KarthikeyaKollu commented on GitHub (Jul 30, 2024):

Hey there, im the founder of that Extension Reachout to me at https://www.linkedin.com/in/karthikeyakollu/

<!-- gh-comment-id:2257480072 --> @KarthikeyaKollu commented on GitHub (Jul 30, 2024): Hey there, im the founder of that Extension Reachout to me at https://www.linkedin.com/in/karthikeyakollu/
GiteaMirror commented 2026-04-28 14:20:41 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 12, 2024):

I'm going to go ahead an close this.

<!-- gh-comment-id:2347286723 --> @pdevine commented on GitHub (Sep 12, 2024): I'm going to go ahead an close this.
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 feature request
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#50137
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?