[GH-ISSUE #13060] Panic: failed to sample token. #70709

Closed
opened 2026-05-04 22:40:21 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @merimus on GitHub (Nov 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13060

What is the issue?

Nov 12 10:29:43 primus ollama[1829]: panic: failed to sample token
Nov 12 10:29:43 primus ollama[1829]: goroutine 1065 [running]:
Nov 12 10:29:43 primus ollama[1829]: github.com/ollama/ollama/runner/ollamarunner.(Server).computeBatch(0xc0002290e0, {0x9, {0x64e1f2212c90, 0xc001255080}, {0x64e1f221d0c0, 0xc00d5a54b8}, {0xc001270c08, 0x1d6, 0x25f}, {{0x64e1f221d0c0, ...}, ...}, ...})
Nov 12 10:29:43 primus ollama[1829]: github.com/ollama/ollama/runner/ollamarunner/runner.go:734 +0x1845
Nov 12 10:29:43 primus ollama[1829]: created by github.com/ollama/ollama/runner/ollamarunner.(Server).run in goroutine 50
Nov 12 10:29:43 primus ollama[1829]: github.com/ollama/ollama/runner/ollamarunner/runner.go:430 +0x2cd
Nov 12 10:29:43 primus ollama[1829]: time=2025-11-12T10:29:43.470-05:00 level=ERROR source=server.go:1475 msg="post predict" error="Post "http://127.0.0.1:38697/completion/": EOF"
Nov 12 10:29:43 primus ollama[1829]: [GIN] 2025/11/12 - 10:29:43 | 500 | 26.924292535s | 100.126.29.18 | POST "/v1/chat/completions"
Nov 12 10:29:43 primus ollama[1829]: [GIN] 2025/11/12 - 10:29:43 | 500 | 26.924533615s | 100.126.29.18 | POST "/v1/chat/completions"

ollama -v
ollama version is 0.12.10
using gpt-oss:120b

ESC[37mROCk module is loadedESC[0m

HSA System Attributes

Runtime Version: 1.18
Runtime Ext Version: 1.11
System Timestamp Freq.: 1000.000000MHz
Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model: LARGE
System Endianness: LITTLE
Mwaitx: DISABLED
XNACK enabled: NO
DMAbuf Support: YES
VMM Support: YES

==========
HSA Agents


Agent 1


Name: AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

Relevant log output


OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @merimus on GitHub (Nov 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13060 ### What is the issue? Nov 12 10:29:43 primus ollama[1829]: panic: failed to sample token Nov 12 10:29:43 primus ollama[1829]: goroutine 1065 [running]: Nov 12 10:29:43 primus ollama[1829]: github.com/ollama/ollama/runner/ollamarunner.(Server).computeBatch(0xc0002290e0, {0x9, {0x64e1f2212c90, 0xc001255080}, {0x64e1f221d0c0, 0xc00d5a54b8}, {0xc001270c08, 0x1d6, 0x25f}, {{0x64e1f221d0c0, ...}, ...}, ...}) Nov 12 10:29:43 primus ollama[1829]: github.com/ollama/ollama/runner/ollamarunner/runner.go:734 +0x1845 Nov 12 10:29:43 primus ollama[1829]: created by github.com/ollama/ollama/runner/ollamarunner.(Server).run in goroutine 50 Nov 12 10:29:43 primus ollama[1829]: github.com/ollama/ollama/runner/ollamarunner/runner.go:430 +0x2cd Nov 12 10:29:43 primus ollama[1829]: time=2025-11-12T10:29:43.470-05:00 level=ERROR source=server.go:1475 msg="post predict" error="Post "http://127.0.0.1:38697/completion/": EOF" Nov 12 10:29:43 primus ollama[1829]: [GIN] 2025/11/12 - 10:29:43 | 500 | 26.924292535s | 100.126.29.18 | POST "/v1/chat/completions" Nov 12 10:29:43 primus ollama[1829]: [GIN] 2025/11/12 - 10:29:43 | 500 | 26.924533615s | 100.126.29.18 | POST "/v1/chat/completions" ollama -v ollama version is 0.12.10 using gpt-oss:120b ESC[37mROCk module is loadedESC[0m ===================== HSA System Attributes ===================== Runtime Version: 1.18 Runtime Ext Version: 1.11 System Timestamp Freq.: 1000.000000MHz Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count) Machine Model: LARGE System Endianness: LITTLE Mwaitx: DISABLED XNACK enabled: NO DMAbuf Support: YES VMM Support: YES ========== HSA Agents ========== ******* Agent 1 ******* Name: AMD RYZEN AI MAX+ 395 w/ Radeon 8060S ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-04 22:40:22 -05:00
Author
Owner

@merimus commented on GitHub (Nov 12, 2025):

Tried ollama 0.12.10,9,8
ollama run < prompt.txt
seems to work

Seeing the issue when using goose cli 1.14.0
rollback goose to 1.13.0, same issue.

ollama pull new version of models, same issue.

<!-- gh-comment-id:3522729175 --> @merimus commented on GitHub (Nov 12, 2025): Tried ollama 0.12.10,9,8 ollama run < prompt.txt seems to work Seeing the issue when using goose cli 1.14.0 rollback goose to 1.13.0, same issue. ollama pull new version of models, same issue.
Author
Owner

@rick-github commented on GitHub (Nov 12, 2025):

Please include the full log.

<!-- gh-comment-id:3522753585 --> @rick-github commented on GitHub (Nov 12, 2025): Please include the full log.
Author
Owner

@merimus commented on GitHub (Nov 13, 2025):

does not reproduce today

<!-- gh-comment-id:3528388122 --> @merimus commented on GitHub (Nov 13, 2025): does not reproduce today
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#70709