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 #13935] Error 500 when running glm-4.7-flash with 198k with claude code docker #9118

New Issue
Open
opened 2026-04-12 21:58:16 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-12 21:58:16 -05:00
Owner
Copy Link

Originally created by @kentsuiGitHub on GitHub (Jan 27, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13935

What is the issue?

I run a separate docker for ollama and claude code. I created a custom model based on model glm-4.7-flash for 198k context length. After several successful (200) API call, ollama start to return error 500 and the duration is around 5 minutes. Below is the part of the log.

[GIN] 2026/01/27 - 14:08:52 | 200 | 6m34s | 192.168.12.60 | POST "/v1/messages?beta=true"

time=2026-01-27T14:08:52.336Z level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 refCount=0

time=2026-01-27T14:08:52.336Z level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 duration=1h0m0s

time=2026-01-27T14:09:01.047Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=177952 format=""

time=2026-01-27T14:08:52.823Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c

time=2026-01-27T14:13:52.450Z level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752

time=2026-01-27T14:09:01.388Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=46241 prompt=44640 used=16690 remaining=27950

time=2026-01-27T14:13:52.450Z level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 duration=1h0m0s

[GIN] 2026/01/27 - 14:13:52 | 500 | 4m59s | 192.168.12.60 | POST "/v1/messages?beta=true"

time=2026-01-27T14:13:52.450Z level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 refCount=0

time=2026-01-27T14:13:53.849Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c

time=2026-01-27T14:14:01.965Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=177952 format=""

time=2026-01-27T14:14:02.275Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=45327 prompt=44640 used=16690 remaining=27950

time=2026-01-27T14:18:53.446Z level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752

[GIN] 2026/01/27 - 14:18:53 | 500 | 4m59s | 192.168.12.60 | POST "/v1/messages?beta=true"

time=2026-01-27T14:18:53.446Z level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 duration=1h0m0s

time=2026-01-27T14:18:53.446Z level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 refCount=0

time=2026-01-27T14:18:54.968Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c

time=2026-01-27T14:19:02.898Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=177952 format=""

time=2026-01-27T14:19:03.219Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=45329 prompt=44640 used=16690 remaining=27950

time=2026-01-27T14:23:54.602Z level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752

[GIN] 2026/01/27 - 14:23:54 | 500 | 4m59s | 192.168.12.60 | POST "/v1/messages?beta=true"

time=2026-01-27T14:23:54.603Z level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 duration=1h0m0s

time=2026-01-27T14:23:54.603Z level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 refCount=0

time=2026-01-27T14:23:57.420Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c

time=2026-01-27T14:24:05.784Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=177952 format=""

time=2026-01-27T14:24:06.081Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=45331 prompt=44640 used=18684 remaining=25956

[GIN] 2026/01/27 - 14:28:57 | 500 | 4m59s | 192.168.12.60 | POST "/v1/messages?beta=true"

time=2026-01-27T14:28:57.079Z level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752

time=2026-01-27T14:28:57.079Z level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 duration=1h0m0s

time=2026-01-27T14:28:57.079Z level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 refCount=0

time=2026-01-27T14:29:01.937Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c

time=2026-01-27T14:29:10.062Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=177952 format=""

time=2026-01-27T14:29:10.401Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=45386 prompt=44640 used=16690 remaining=27950

time=2026-01-27T14:34:01.582Z level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752

Relevant log output

OS

Docker

GPU

Other

CPU

Other

Ollama version

0.15.1 with jetpack 6

Originally created by @kentsuiGitHub on GitHub (Jan 27, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13935 ### What is the issue? I run a separate docker for ollama and claude code. I created a custom model based on model glm-4.7-flash for 198k context length. After several successful (200) API call, ollama start to return error 500 and the duration is around 5 minutes. Below is the part of the log. [GIN] 2026/01/27 - 14:08:52 | 200 | 6m34s | 192.168.12.60 | POST "/v1/messages?beta=true" time=2026-01-27T14:08:52.336Z level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 refCount=0 time=2026-01-27T14:08:52.336Z level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 duration=1h0m0s time=2026-01-27T14:09:01.047Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=177952 format="" time=2026-01-27T14:08:52.823Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c time=2026-01-27T14:13:52.450Z level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 time=2026-01-27T14:09:01.388Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=46241 prompt=44640 used=16690 remaining=27950 time=2026-01-27T14:13:52.450Z level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 duration=1h0m0s [GIN] 2026/01/27 - 14:13:52 | 500 | 4m59s | 192.168.12.60 | POST "/v1/messages?beta=true" time=2026-01-27T14:13:52.450Z level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 refCount=0 time=2026-01-27T14:13:53.849Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c time=2026-01-27T14:14:01.965Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=177952 format="" time=2026-01-27T14:14:02.275Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=45327 prompt=44640 used=16690 remaining=27950 time=2026-01-27T14:18:53.446Z level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 [GIN] 2026/01/27 - 14:18:53 | 500 | 4m59s | 192.168.12.60 | POST "/v1/messages?beta=true" time=2026-01-27T14:18:53.446Z level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 duration=1h0m0s time=2026-01-27T14:18:53.446Z level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 refCount=0 time=2026-01-27T14:18:54.968Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c time=2026-01-27T14:19:02.898Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=177952 format="" time=2026-01-27T14:19:03.219Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=45329 prompt=44640 used=16690 remaining=27950 time=2026-01-27T14:23:54.602Z level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 [GIN] 2026/01/27 - 14:23:54 | 500 | 4m59s | 192.168.12.60 | POST "/v1/messages?beta=true" time=2026-01-27T14:23:54.603Z level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 duration=1h0m0s time=2026-01-27T14:23:54.603Z level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 refCount=0 time=2026-01-27T14:23:57.420Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c time=2026-01-27T14:24:05.784Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=177952 format="" time=2026-01-27T14:24:06.081Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=45331 prompt=44640 used=18684 remaining=25956 [GIN] 2026/01/27 - 14:28:57 | 500 | 4m59s | 192.168.12.60 | POST "/v1/messages?beta=true" time=2026-01-27T14:28:57.079Z level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 time=2026-01-27T14:28:57.079Z level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 duration=1h0m0s time=2026-01-27T14:28:57.079Z level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 refCount=0 time=2026-01-27T14:29:01.937Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c time=2026-01-27T14:29:10.062Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=177952 format="" time=2026-01-27T14:29:10.401Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=45386 prompt=44640 used=16690 remaining=27950 time=2026-01-27T14:34:01.582Z level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/library/glm-4.7-flash:q8-198k runner.inference="[{ID:GPU-39bc44a2-5293-57f9-a322-74b8fccb5150 Library:CUDA}]" runner.size="41.1 GiB" runner.vram="41.1 GiB" runner.parallel=1 runner.pid=87 runner.model=/ollama/blobs/sha256-1bfdff04a01e06051d7dcf5bcd6d7486240e1a92d2ce3325f727a20f2965e68c runner.num_ctx=202752 ### Relevant log output ```shell ``` ### OS Docker ### GPU Other ### CPU Other ### Ollama version 0.15.1 with jetpack 6
GiteaMirror added the bug label 2026-04-12 21:58:16 -05:00
GiteaMirror commented 2026-04-12 21:58:17 -05:00
Author
Owner
Copy Link

@kentsuiGitHub commented on GitHub (Jan 27, 2026):

When load the model , key not found is identified in the log.

time=2026-01-27T16:45:31.145Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32

time=2026-01-27T16:45:37.280Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=glm4moelite.pooling_type default=0

time=2026-01-27T16:45:37.280Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false

time=2026-01-27T16:45:37.280Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0

<!-- gh-comment-id:3806303949 --> @kentsuiGitHub commented on GitHub (Jan 27, 2026): When load the model , key not found is identified in the log. time=2026-01-27T16:45:31.145Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 time=2026-01-27T16:45:37.280Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=glm4moelite.pooling_type default=0 time=2026-01-27T16:45:37.280Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false time=2026-01-27T16:45:37.280Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
GiteaMirror commented 2026-04-12 21:58:18 -05:00
Author
Owner
Copy Link

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

It's likely the prompt from Claude Code is large and the model doesn't finish before CC triggers a timeout and disconnects.

<!-- gh-comment-id:3807846530 --> @rick-github commented on GitHub (Jan 27, 2026): It's likely the prompt from Claude Code is large and the model doesn't finish before CC triggers a timeout and disconnects.
GiteaMirror commented 2026-04-12 21:58:19 -05:00
Author
Owner
Copy Link

@kentsuiGitHub commented on GitHub (Jan 28, 2026):

Added below to claude code to extend the timeout but the error is still exist.
{
"env": {
"BASH_DEFAULT_TIMEOUT_MS": "1800000", // 30 minutes
"BASH_MAX_TIMEOUT_MS": "7200000" // 120 minutes max
}

<!-- gh-comment-id:3808353930 --> @kentsuiGitHub commented on GitHub (Jan 28, 2026): Added below to claude code to extend the timeout but the error is still exist. { "env": { "BASH_DEFAULT_TIMEOUT_MS": "1800000", // 30 minutes "BASH_MAX_TIMEOUT_MS": "7200000" // 120 minutes max }
GiteaMirror commented 2026-04-12 21:58:20 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 28, 2026):

API timeout, not bash timeout.

<!-- gh-comment-id:3809351911 --> @rick-github commented on GitHub (Jan 28, 2026): API timeout, not bash timeout.
GiteaMirror commented 2026-04-12 21:58:20 -05:00
Author
Owner
Copy Link

@kentsuiGitHub commented on GitHub (Jan 28, 2026):

Suspect error 500 is due to context lenght is too large (>198k) because running /clear in Claude Code will resume the implementation.

<!-- gh-comment-id:3811439349 --> @kentsuiGitHub commented on GitHub (Jan 28, 2026): Suspect error 500 is due to context lenght is too large (>198k) because running /clear in Claude Code will resume the implementation.
GiteaMirror commented 2026-04-12 21:58:21 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 28, 2026):

Suspect error 500 is due to context lenght is too large (>198k) because running /clear in Claude Code will resume the implementation.

https://github.com/ollama/ollama/issues/13935#issuecomment-3807846530

<!-- gh-comment-id:3811462018 --> @rick-github commented on GitHub (Jan 28, 2026): > Suspect error 500 is due to context lenght is too large (>198k) because running /clear in Claude Code will resume the implementation. https://github.com/ollama/ollama/issues/13935#issuecomment-3807846530
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#9118
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?