[GH-ISSUE #6501] llama_get_logits_ith: invalid logits id 11, reason: no logits #50604

Open
opened 2026-04-28 16:29:10 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @zhaowanjin on GitHub (Aug 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6501

What is the issue?

llama_get_logits_ith: invalid logits id 11, reason: no logits

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

No response

Originally created by @zhaowanjin on GitHub (Aug 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6501 ### What is the issue? llama_get_logits_ith: invalid logits id 11, reason: no logits ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-28 16:29:10 -05:00
Author
Owner

@rick-github commented on GitHub (Aug 25, 2024):

Server logs will aid in debugging, but it would be helpful if you could provide context.

<!-- gh-comment-id:2308894943 --> @rick-github commented on GitHub (Aug 25, 2024): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will aid in debugging, but it would be helpful if you could provide context.
Author
Owner

@zhaowanjin commented on GitHub (Aug 25, 2024):

time=2024-08-25T23:29:34.047+08:00 level=INFO source=server.go:567 msg="llama runner started in 33.88 seconds"
[GIN] 2024/08/25 - 23:29:34 | 200 | 34.812771654s | 127.0.0.1 | POST "/api/chat"
[1724599846] uhd_slice_image: multiple 9
[1724599846] uhd_slice_image: image_size: 1920 1440; source_image size: 518 392
[1724599846] uhd_slice_image: image_size: 1920 1440; best_grid: 3 3
[1724599846] uhd_slice_image: refine_image_size: 1554 1176; refine_size: 1554 1176
[1724599846] clip_image_preprocess: 518 392
[1724599846] clip_image_preprocess: 518 392
[1724599846] clip_image_preprocess: 518 392
[1724599847] clip_image_preprocess: 518 392
[1724599847] clip_image_preprocess: 518 392
[1724599847] clip_image_preprocess: 518 392
[1724599847] clip_image_preprocess: 518 392
[1724599847] clip_image_preprocess: 518 392
[1724599847] clip_image_preprocess: 518 392
[1724599847] clip_image_preprocess: 518 392
[1724599847] clip_image_build_graph: 518 392
[1724599847] encode_image_with_clip: step 1 of 10 encoded in 127.88 ms
[1724599847] clip_image_build_graph: 518 392
[1724599847] encode_image_with_clip: step 2 of 10 encoded in 80.28 ms
[1724599847] clip_image_build_graph: 518 392
[1724599847] encode_image_with_clip: step 3 of 10 encoded in 76.35 ms
[1724599847] clip_image_build_graph: 518 392
[1724599847] encode_image_with_clip: step 4 of 10 encoded in 69.31 ms
[1724599847] clip_image_build_graph: 518 392
[1724599847] encode_image_with_clip: step 5 of 10 encoded in 68.69 ms
[1724599847] clip_image_build_graph: 518 392
[1724599847] encode_image_with_clip: step 6 of 10 encoded in 67.99 ms
[1724599847] clip_image_build_graph: 518 392
[1724599847] encode_image_with_clip: step 7 of 10 encoded in 68.63 ms
[1724599847] clip_image_build_graph: 518 392
[1724599847] encode_image_with_clip: step 8 of 10 encoded in 68.64 ms
[1724599847] clip_image_build_graph: 518 392
[1724599847] encode_image_with_clip: step 9 of 10 encoded in 68.93 ms
[1724599847] clip_image_build_graph: 518 392
[1724599847] encode_image_with_clip: step 10 of 10 encoded in 68.26 ms
[1724599847] encode_image_with_clip: all 10 segments encoded in 765.10 ms
[1724599847] encode_image_with_clip: load_image_size 1920 1440
[1724599847] encode_image_with_clip: image embedding created: 960 tokens
[1724599847]
encode_image_with_clip: image encoded in 767.04 ms by CLIP ( 0.80 ms per image patch)
llama_get_logits_ith: invalid logits id 9, reason: no logits
[GIN] 2024/08/25 - 23:30:48 | 200 | 2.571823672s | 127.0.0.1 | POST "/api/chat"

issues

<!-- gh-comment-id:2308898889 --> @zhaowanjin commented on GitHub (Aug 25, 2024): time=2024-08-25T23:29:34.047+08:00 level=INFO source=server.go:567 msg="llama runner started in 33.88 seconds" [GIN] 2024/08/25 - 23:29:34 | 200 | 34.812771654s | 127.0.0.1 | POST "/api/chat" [1724599846] uhd_slice_image: multiple 9 [1724599846] uhd_slice_image: image_size: 1920 1440; source_image size: 518 392 [1724599846] uhd_slice_image: image_size: 1920 1440; best_grid: 3 3 [1724599846] uhd_slice_image: refine_image_size: 1554 1176; refine_size: 1554 1176 [1724599846] clip_image_preprocess: 518 392 [1724599846] clip_image_preprocess: 518 392 [1724599846] clip_image_preprocess: 518 392 [1724599847] clip_image_preprocess: 518 392 [1724599847] clip_image_preprocess: 518 392 [1724599847] clip_image_preprocess: 518 392 [1724599847] clip_image_preprocess: 518 392 [1724599847] clip_image_preprocess: 518 392 [1724599847] clip_image_preprocess: 518 392 [1724599847] clip_image_preprocess: 518 392 [1724599847] clip_image_build_graph: 518 392 [1724599847] encode_image_with_clip: step 1 of 10 encoded in 127.88 ms [1724599847] clip_image_build_graph: 518 392 [1724599847] encode_image_with_clip: step 2 of 10 encoded in 80.28 ms [1724599847] clip_image_build_graph: 518 392 [1724599847] encode_image_with_clip: step 3 of 10 encoded in 76.35 ms [1724599847] clip_image_build_graph: 518 392 [1724599847] encode_image_with_clip: step 4 of 10 encoded in 69.31 ms [1724599847] clip_image_build_graph: 518 392 [1724599847] encode_image_with_clip: step 5 of 10 encoded in 68.69 ms [1724599847] clip_image_build_graph: 518 392 [1724599847] encode_image_with_clip: step 6 of 10 encoded in 67.99 ms [1724599847] clip_image_build_graph: 518 392 [1724599847] encode_image_with_clip: step 7 of 10 encoded in 68.63 ms [1724599847] clip_image_build_graph: 518 392 [1724599847] encode_image_with_clip: step 8 of 10 encoded in 68.64 ms [1724599847] clip_image_build_graph: 518 392 [1724599847] encode_image_with_clip: step 9 of 10 encoded in 68.93 ms [1724599847] clip_image_build_graph: 518 392 [1724599847] encode_image_with_clip: step 10 of 10 encoded in 68.26 ms [1724599847] encode_image_with_clip: all 10 segments encoded in 765.10 ms [1724599847] encode_image_with_clip: load_image_size 1920 1440 [1724599847] encode_image_with_clip: image embedding created: 960 tokens [1724599847] encode_image_with_clip: image encoded in 767.04 ms by CLIP ( 0.80 ms per image patch) llama_get_logits_ith: invalid logits id 9, reason: no logits [GIN] 2024/08/25 - 23:30:48 | 200 | 2.571823672s | 127.0.0.1 | POST "/api/chat" ![issues](https://github.com/user-attachments/assets/9eab1c9c-ad0f-4eb0-a089-2753517c8734)
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#50604