github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14088] qwen3 next no working in 0.15.5 when i config OLLAMA_NUM_PARALLEL=2 #14087 #71259

New Issue
Open
opened 2026-05-05 00:58:25 -05:00 by GiteaMirror · 10 comments
GiteaMirror commented 2026-05-05 00:58:25 -05:00
Owner
Copy Link

Originally created by @r4c0box on GitHub (Feb 5, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14088

Originally assigned to: @jmorganca on GitHub.

What is the issue?

What is the issue?

In mycase, when i test Environment="OLLAMA_NUM_PARALLEL=num" in /etc/systemd/system/ollama.service start to use qwen3-coder-next:latest, it is always report "
Error: 500 Internal Server Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details
", i try it several times ，and it still the same error。but if i not set this Evironment ，it work well。

Relevant log output

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.15.5-rc3

Originally created by @r4c0box on GitHub (Feb 5, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14088 Originally assigned to: @jmorganca on GitHub. ### What is the issue? What is the issue? In mycase, when i test Environment="OLLAMA_NUM_PARALLEL=num" in /etc/systemd/system/ollama.service start to use qwen3-coder-next:latest, it is always report " Error: 500 Internal Server Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details ", i try it several times ，and it still the same error。but if i not set this Evironment ，it work well。 ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.15.5-rc3
GiteaMirror added the bug label 2026-05-05 00:58:26 -05:00
GiteaMirror commented 2026-05-05 00:58:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 5, 2026):

Server logs may aid in debugging.

<!-- gh-comment-id:3851146502 --> @rick-github commented on GitHub (Feb 5, 2026): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.mdx) may aid in debugging.
GiteaMirror commented 2026-05-05 00:58:35 -05:00
Author
Owner
Copy Link

@r4c0box commented on GitHub (Feb 5, 2026):

2月 05 14:28:04 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:28:04 | 200 | 5.017413597s | 192.168.5.1 | POST "/v1/messages?beta=true"
2月 05 14:28:29 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:28:29 | 404 | 273.601µs | 192.168.5.1 | POST "/v1/messages?beta=true"
2月 05 14:29:28 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:29:28 | 200 | 5.762331753s | 192.168.5.1 | POST "/api/chat"
2月 05 14:29:44 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:29:44 | 404 | 279.679µs | 192.168.5.1 | POST "/v1/messages?beta=true"
2月 05 14:29:44 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:44.967+08:00 level=WARN source=routes.go:2093 msg="model does not support thinking, relaxing thinking to nil" model=qwen3-coder-next:latest
2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: panic: failed to build graph: model does not support operation
2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: goroutine 11 [running]:
2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0002330e0, {0x58942f7cb020, 0xc000378280})
2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: github.com/ollama/ollama/runner/ollamarunner/runner.go:454 +0x325
2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: github.com/ollama/ollama/runner/ollamarunner/runner.go:1422 +0x4c9
2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:45.578+08:00 level=ERROR source=server.go:1609 msg="post predict" error="Post "http://127.0.0.1:35767/completion": EOF"
2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:29:45 | 500 | 676.722835ms | 192.168.5.1 | POST "/v1/messages?beta=true"
2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:29:45 | 200 | 1.071997839s | 192.168.5.1 | POST "/api/chat"
2月 05 14:29:46 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:46.256+08:00 level=WARN source=routes.go:2093 msg="model does not support thinking, relaxing thinking to nil" model=qwen3-coder-next:latest
2月 05 14:29:46 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:46.321+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42109"
2月 05 14:29:46 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:46.978+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 36867"
2月 05 14:29:47 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:47.399+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 44839"
2月 05 14:29:47 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:47.931+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 38613"
2月 05 14:29:48 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:48.557+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 37609"
2月 05 14:29:49 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:49.223+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 43333"
2月 05 14:29:49 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:49.887+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 34481"
2月 05 14:29:50 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:50.593+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 38669"
2月 05 14:29:51 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:51.316+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 35331"
2月 05 14:29:51 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:51.728+08:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" extra_envs=map[] error="failed to finish discovery before timeout"
2月 05 14:29:51 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:51.728+08:00 level=WARN source=runner.go:356 msg="unable to refresh free memory, using old values"
2月 05 14:29:51 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:51.728+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 40683"
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.380+08:00 level=INFO source=server.go:246 msg="enabling flash attention"
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-30e51a7cb1cf1333b9e298b90b4c7790fe2572d8736b002482a0ac96328a2ffb --port 36421"
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=sched.go:463 msg="system memory" total="61.3 GiB" free="57.4 GiB" free_swap="8.0 GiB"
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=sched.go:470 msg="gpu memory" id=GPU-973dab5e-041e-d47f-5b51-27c124287be6 library=CUDA available="20.8 GiB" free="21.3 GiB" minimum="457.0 MiB" overhead="0 B"
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=sched.go:470 msg="gpu memory" id=GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4 library=CUDA available="20.9 GiB" free="21.3 GiB" minimum="457.0 MiB" overhead="0 B"
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=sched.go:470 msg="gpu memory" id=GPU-0e6bd110-64ab-b976-743a-2ec6e22ec500 library=CUDA available="20.9 GiB" free="21.3 GiB" minimum="457.0 MiB" overhead="0 B"
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=server.go:756 msg="loading model" "model layers"=49 requested=-1
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.388+08:00 level=INFO source=runner.go:1409 msg="starting ollama engine"
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.388+08:00 level=INFO source=runner.go:1444 msg="Server listening on 127.0.0.1:36421"
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.392+08:00 level=INFO source=runner.go:1282 msg=load request="{Operation:fit LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:4 GPULayers:49[ID:GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4 Layers:49(0..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.416+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3next file_type=Q4_K_M name="" description="" num_tensors=843 num_key_values=38
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: ggml_cuda_init: found 3 CUDA devices:
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: Device 0: NVIDIA GeForce RTX 2080 Ti, compute capability 7.5, VMM: yes, ID: GPU-973dab5e-041e-d47f-5b51-27c124287be6
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: Device 1: NVIDIA GeForce RTX 2080 Ti, compute capability 7.5, VMM: yes, ID: GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: Device 2: NVIDIA GeForce RTX 2080 Ti, compute capability 7.5, VMM: yes, ID: GPU-0e6bd110-64ab-b976-743a-2ec6e22ec500
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v13/libggml-cuda.so
2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.752+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 CUDA.1.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.1.USE_GRAPHS=1 CUDA.1.PEER_MAX_BATCH_SIZE=128 CUDA.2.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.2.USE_GRAPHS=1 CUDA.2.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.207+08:00 level=INFO source=runner.go:1282 msg=load request="{Operation:fit LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:4 GPULayers:49[ID:GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4 Layers:16(0..15) ID:GPU-0e6bd110-64ab-b976-743a-2ec6e22ec500 Layers:16(16..31) ID:GPU-973dab5e-041e-d47f-5b51-27c124287be6 Layers:17(32..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.647+08:00 level=INFO source=runner.go:1282 msg=load request="{Operation:alloc LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:4 GPULayers:49[ID:GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4 Layers:16(0..15) ID:GPU-0e6bd110-64ab-b976-743a-2ec6e22ec500 Layers:16(16..31) ID:GPU-973dab5e-041e-d47f-5b51-27c124287be6 Layers:17(32..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=runner.go:1282 msg=load request="{Operation:commit LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:4 GPULayers:49[ID:GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4 Layers:16(0..15) ID:GPU-0e6bd110-64ab-b976-743a-2ec6e22ec500 Layers:16(16..31) ID:GPU-973dab5e-041e-d47f-5b51-27c124287be6 Layers:17(32..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=ggml.go:482 msg="offloading 48 repeating layers to GPU"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=ggml.go:494 msg="offloaded 49/49 layers to GPU"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="16.2 GiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA1 size="15.9 GiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA2 size="15.9 GiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="166.9 MiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="2.1 GiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA1 size="2.1 GiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA2 size="2.1 GiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="220.4 MiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA1 size="318.2 MiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA2 size="220.4 MiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="4.3 MiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:272 msg="total memory" size="55.3 GiB"
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=sched.go:537 msg="loaded runners" count=1
2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=server.go:1349 msg="waiting for llama runner to start responding"
2月 05 14:29:54 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.999+08:00 level=INFO source=server.go:1383 msg="waiting for server to become available" status="llm server loading model"
2月 05 14:30:06 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:30:06.788+08:00 level=INFO source=server.go:1387 msg="llama runner started in 14.41 seconds"
2月 05 14:30:35 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:30:35 | 200 | 49.099064684s | 192.168.5.1 | POST "/v1/messages?beta=true"
2月 05 14:30:35 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:30:35.449+08:00 level=WARN source=routes.go:2093 msg="model does not support thinking, relaxing thinking to nil" model=qwen3-coder-next:latest
2月 05 14:30:42 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:30:42 | 200 | 7.193161067s | 192.168.5.1 | POST "/v1/messages?beta=true"

<!-- gh-comment-id:3851341457 --> @r4c0box commented on GitHub (Feb 5, 2026): 2月 05 14:28:04 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:28:04 | 200 | 5.017413597s | 192.168.5.1 | POST "/v1/messages?beta=true" 2月 05 14:28:29 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:28:29 | 404 | 273.601µs | 192.168.5.1 | POST "/v1/messages?beta=true" 2月 05 14:29:28 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:29:28 | 200 | 5.762331753s | 192.168.5.1 | POST "/api/chat" 2月 05 14:29:44 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:29:44 | 404 | 279.679µs | 192.168.5.1 | POST "/v1/messages?beta=true" 2月 05 14:29:44 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:44.967+08:00 level=WARN source=routes.go:2093 msg="model does not support thinking, relaxing thinking to nil" model=qwen3-coder-next:latest 2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: panic: failed to build graph: model does not support operation 2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: goroutine 11 [running]: 2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0002330e0, {0x58942f7cb020, 0xc000378280}) 2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: github.com/ollama/ollama/runner/ollamarunner/runner.go:454 +0x325 2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: github.com/ollama/ollama/runner/ollamarunner/runner.go:1422 +0x4c9 2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:45.578+08:00 level=ERROR source=server.go:1609 msg="post predict" error="Post \"http://127.0.0.1:35767/completion\": EOF" 2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:29:45 | 500 | 676.722835ms | 192.168.5.1 | POST "/v1/messages?beta=true" 2月 05 14:29:45 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:29:45 | 200 | 1.071997839s | 192.168.5.1 | POST "/api/chat" 2月 05 14:29:46 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:46.256+08:00 level=WARN source=routes.go:2093 msg="model does not support thinking, relaxing thinking to nil" model=qwen3-coder-next:latest 2月 05 14:29:46 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:46.321+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42109" 2月 05 14:29:46 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:46.978+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 36867" 2月 05 14:29:47 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:47.399+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 44839" 2月 05 14:29:47 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:47.931+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 38613" 2月 05 14:29:48 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:48.557+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 37609" 2月 05 14:29:49 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:49.223+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 43333" 2月 05 14:29:49 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:49.887+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 34481" 2月 05 14:29:50 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:50.593+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 38669" 2月 05 14:29:51 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:51.316+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 35331" 2月 05 14:29:51 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:51.728+08:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" extra_envs=map[] error="failed to finish discovery before timeout" 2月 05 14:29:51 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:51.728+08:00 level=WARN source=runner.go:356 msg="unable to refresh free memory, using old values" 2月 05 14:29:51 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:51.728+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 40683" 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.380+08:00 level=INFO source=server.go:246 msg="enabling flash attention" 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=server.go:430 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-30e51a7cb1cf1333b9e298b90b4c7790fe2572d8736b002482a0ac96328a2ffb --port 36421" 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=sched.go:463 msg="system memory" total="61.3 GiB" free="57.4 GiB" free_swap="8.0 GiB" 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=sched.go:470 msg="gpu memory" id=GPU-973dab5e-041e-d47f-5b51-27c124287be6 library=CUDA available="20.8 GiB" free="21.3 GiB" minimum="457.0 MiB" overhead="0 B" 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=sched.go:470 msg="gpu memory" id=GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4 library=CUDA available="20.9 GiB" free="21.3 GiB" minimum="457.0 MiB" overhead="0 B" 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=sched.go:470 msg="gpu memory" id=GPU-0e6bd110-64ab-b976-743a-2ec6e22ec500 library=CUDA available="20.9 GiB" free="21.3 GiB" minimum="457.0 MiB" overhead="0 B" 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.381+08:00 level=INFO source=server.go:756 msg="loading model" "model layers"=49 requested=-1 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.388+08:00 level=INFO source=runner.go:1409 msg="starting ollama engine" 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.388+08:00 level=INFO source=runner.go:1444 msg="Server listening on 127.0.0.1:36421" 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.392+08:00 level=INFO source=runner.go:1282 msg=load request="{Operation:fit LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:4 GPULayers:49[ID:GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4 Layers:49(0..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.416+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3next file_type=Q4_K_M name="" description="" num_tensors=843 num_key_values=38 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: ggml_cuda_init: found 3 CUDA devices: 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: Device 0: NVIDIA GeForce RTX 2080 Ti, compute capability 7.5, VMM: yes, ID: GPU-973dab5e-041e-d47f-5b51-27c124287be6 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: Device 1: NVIDIA GeForce RTX 2080 Ti, compute capability 7.5, VMM: yes, ID: GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: Device 2: NVIDIA GeForce RTX 2080 Ti, compute capability 7.5, VMM: yes, ID: GPU-0e6bd110-64ab-b976-743a-2ec6e22ec500 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v13/libggml-cuda.so 2月 05 14:29:52 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:52.752+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 CUDA.1.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.1.USE_GRAPHS=1 CUDA.1.PEER_MAX_BATCH_SIZE=128 CUDA.2.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.2.USE_GRAPHS=1 CUDA.2.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.207+08:00 level=INFO source=runner.go:1282 msg=load request="{Operation:fit LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:4 GPULayers:49[ID:GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4 Layers:16(0..15) ID:GPU-0e6bd110-64ab-b976-743a-2ec6e22ec500 Layers:16(16..31) ID:GPU-973dab5e-041e-d47f-5b51-27c124287be6 Layers:17(32..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.647+08:00 level=INFO source=runner.go:1282 msg=load request="{Operation:alloc LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:4 GPULayers:49[ID:GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4 Layers:16(0..15) ID:GPU-0e6bd110-64ab-b976-743a-2ec6e22ec500 Layers:16(16..31) ID:GPU-973dab5e-041e-d47f-5b51-27c124287be6 Layers:17(32..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=runner.go:1282 msg=load request="{Operation:commit LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:4 GPULayers:49[ID:GPU-3b1956ff-7570-052e-c344-9d8d2ea409d4 Layers:16(0..15) ID:GPU-0e6bd110-64ab-b976-743a-2ec6e22ec500 Layers:16(16..31) ID:GPU-973dab5e-041e-d47f-5b51-27c124287be6 Layers:17(32..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=ggml.go:482 msg="offloading 48 repeating layers to GPU" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=ggml.go:494 msg="offloaded 49/49 layers to GPU" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="16.2 GiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA1 size="15.9 GiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA2 size="15.9 GiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="166.9 MiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="2.1 GiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA1 size="2.1 GiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA2 size="2.1 GiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="220.4 MiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA1 size="318.2 MiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA2 size="220.4 MiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="4.3 MiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=device.go:272 msg="total memory" size="55.3 GiB" 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=sched.go:537 msg="loaded runners" count=1 2月 05 14:29:53 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.982+08:00 level=INFO source=server.go:1349 msg="waiting for llama runner to start responding" 2月 05 14:29:54 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:29:53.999+08:00 level=INFO source=server.go:1383 msg="waiting for server to become available" status="llm server loading model" 2月 05 14:30:06 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:30:06.788+08:00 level=INFO source=server.go:1387 msg="llama runner started in 14.41 seconds" 2月 05 14:30:35 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:30:35 | 200 | 49.099064684s | 192.168.5.1 | POST "/v1/messages?beta=true" 2月 05 14:30:35 test-B760M-Snow-Dream-wifi-W ollama[18718]: time=2026-02-05T14:30:35.449+08:00 level=WARN source=routes.go:2093 msg="model does not support thinking, relaxing thinking to nil" model=qwen3-coder-next:latest 2月 05 14:30:42 test-B760M-Snow-Dream-wifi-W ollama[18718]: [GIN] 2026/02/05 - 14:30:42 | 200 | 7.193161067s | 192.168.5.1 | POST "/v1/messages?beta=true"
GiteaMirror commented 2026-05-05 00:58:37 -05:00
Author
Owner
Copy Link

@r4c0box commented on GitHub (Feb 5, 2026):

when i use two client answer question at time same time，it course the error like the log above

<!-- gh-comment-id:3851347736 --> @r4c0box commented on GitHub (Feb 5, 2026): when i use two client answer question at time same time，it course the error like the log above
GiteaMirror commented 2026-05-05 00:58:38 -05:00
Author
Owner
Copy Link

@znowfox commented on GitHub (Feb 5, 2026):

So, 0.15.5 RC1 worked, stopped working rc2, rc3.

<!-- gh-comment-id:3851645672 --> @znowfox commented on GitHub (Feb 5, 2026): So, 0.15.5 RC1 worked, stopped working rc2, rc3.
GiteaMirror commented 2026-05-05 00:58:39 -05:00
Author
Owner
Copy Link

@r4c0box commented on GitHub (Feb 5, 2026):

So, 0.15.5 RC1 worked, stopped working rc2, rc3.

ok，i will try rc1 to test again

<!-- gh-comment-id:3851666958 --> @r4c0box commented on GitHub (Feb 5, 2026): > So, 0.15.5 RC1 worked, stopped working rc2, rc3. ok，i will try rc1 to test again
GiteaMirror commented 2026-05-05 00:58:41 -05:00
Author
Owner
Copy Link

@r4c0box commented on GitHub (Feb 5, 2026):

but，i cannot find the rc1 package in releases 。。。。

<!-- gh-comment-id:3851828806 --> @r4c0box commented on GitHub (Feb 5, 2026): but，i cannot find the rc1 package in releases 。。。。
GiteaMirror commented 2026-05-05 00:58:42 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 5, 2026):

The -rc releases have new default context logic that doesn't account for OLLAMA_NUM_PARALLEL. Until it's resolved, setting OLLAMA_CONTEXT_LENGTH=4096 in the server environment will return to the previous behaviour.

<!-- gh-comment-id:3854417199 --> @rick-github commented on GitHub (Feb 5, 2026): The `-rc` releases have new default context logic that doesn't account for `OLLAMA_NUM_PARALLEL`. Until it's resolved, setting `OLLAMA_CONTEXT_LENGTH=4096` in the server environment will return to the previous behaviour.
GiteaMirror commented 2026-05-05 00:58:44 -05:00
Author
Owner
Copy Link

@znowfox commented on GitHub (Feb 5, 2026):

so obviously its llama.cpp

<!-- gh-comment-id:3854944095 --> @znowfox commented on GitHub (Feb 5, 2026): so obviously its llama.cpp
GiteaMirror commented 2026-05-05 00:58:47 -05:00
Author
Owner
Copy Link

@fighter3005 commented on GitHub (Feb 27, 2026):

Sorry to chime in here, but I am confused. I tried setting OLLAMA_NUM_PARALLEL and OLLAMA_CONTEXT_LENGTH=4096 in my docker compose environment variables, and also setting just OLLAMA_NUM_PARALLEL, but OLLAMA_NUM_PARALLEL is being ignored regardless!?
I tried with the rocm and cuda containers in the latest version (0.17.4).
I tested qwen3-vl:4b-instruct-q8_0 and qwen3.5:27b-q4_K_M, as well as bge-m3:567m-fp16.
I don't get parallelism.

<!-- gh-comment-id:3975126828 --> @fighter3005 commented on GitHub (Feb 27, 2026): Sorry to chime in here, but I am confused. I tried setting OLLAMA_NUM_PARALLEL and OLLAMA_CONTEXT_LENGTH=4096 in my docker compose environment variables, and also setting just OLLAMA_NUM_PARALLEL, but OLLAMA_NUM_PARALLEL is being ignored regardless!? I tried with the rocm and cuda containers in the latest version (0.17.4). I tested qwen3-vl:4b-instruct-q8_0 and qwen3.5:27b-q4_K_M, as well as bge-m3:567m-fp16. I don't get parallelism.
GiteaMirror commented 2026-05-05 00:58:49 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 27, 2026):

Some model architectures do not support parallelism.

<!-- gh-comment-id:3975691107 --> @rick-github commented on GitHub (Feb 27, 2026): Some model architectures [do not support](https://github.com/ollama/ollama/blob/dd5eb6337dab84d76d7edec2c102064504d75378/server/sched.go#L450) parallelism.
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 bug
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#71259
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?