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 #13402] Embedding will not work with some models #34610

New Issue
Closed
opened 2026-04-22 18:19:44 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-22 18:19:44 -05:00
Owner
Copy Link

Originally created by @alienatorZ on GitHub (Dec 10, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13402

Originally assigned to: @jessegross on GitHub.

What is the issue?

I have Ubuntu 22.04
Ollama 0.13.3-rc0

with models like gpt-oss and qwen3 30ba3b I get:

time=2025-12-10T01:05:16.820Z level=INFO source=server.go:1332 msg="llama runner started in 0.55 seconds"
panic: caching disabled but unable to fit entire input in a batch

goroutine 8 [running]:
github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc00021d0e0, {0x0, {0x5d17aac04d30, 0xc000690100}, {0x5d17aac0f1a0, 0xc000011308}, {0xc0001e9908, 0x200, 0x25f}, {{0x5d17aac0f1a0, ...}, ...}, ...})
github.com/ollama/ollama/runner/ollamarunner/runner.go:707 +0x1ac5
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc00021d0e0, {0x5d17aabfa2a0, 0xc00036e0a0})
github.com/ollama/ollama/runner/ollamarunner/runner.go:460 +0x30b
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
github.com/ollama/ollama/runner/ollamarunner/runner.go:1412 +0x4c9
[GIN] 2025/12/10 - 01:05:16 | 400 | 662.671261ms | 127.0.0.1 | POST "/v1/embeddings"
ggml_backend_cuda_device_get_memory device GPU-3db830a0-9e60-5a10-12d2-610d17f21eda utilizing NVML memory reporting free: 9562619904 total: 25769803776
ggml_backend_cuda_device_get_memory device GPU-9d2aa8d9-e445-799f-a8e6-8613d292be49 utilizing NVML memory reporting free: 9516482560 total: 25769803776
time=2025-12-10T01:10:16.523Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 39367"
time=2025-12-10T01:10:16.902Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 45263"
time=2025-12-10T01:10:17.386Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41443"
time=2025-12-10T01:10:17.637Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40973"
time=2025-12-10T01:10:17.887Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41359"
time=2025-12-10T01:10:18.137Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40929"
time=2025-12-10T01:10:18.387Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 44135"
time=2025-12-10T01:10:18.637Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40651"
time=2025-12-10T01:10:18.887Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 44351"
time=2025-12-10T01:10:19.137Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37923"
time=2025-12-10T01:10:19.387Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46833"
time=2025-12-10T01:10:19.637Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42845"
time=2025-12-10T01:10:19.887Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40909"
time=2025-12-10T01:10:20.137Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 39489"
time=2025-12-10T01:10:20.387Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41233"
time=2025-12-10T01:10:20.637Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40639"
time=2025-12-10T01:10:20.887Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41111"
time=2025-12-10T01:10:21.137Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 43361"
time=2025-12-10T01:10:21.387Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40575"
time=2025-12-10T01:10:21.636Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37059"
time=2025-12-10T01:10:21.887Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41903"
time=2025-12-10T01:10:22.137Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37109"
time=2025-12-10T01:10:22.138Z level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout"
time=2025-12-10T01:10:22.138Z level=WARN source=runner.go:356 msg="unable to refresh free memory, using old values"
[GIN] 2025/12/10 - 02:11:11 | 200 | 40.105µs | 127.0.0.1 | GET "/api/version"

Relevant log output

OS

Ubuntu 22.04

GPU

Nvidia Tesla P40 X2

CPU

No response

Ollama version

0.13.3-rc0

Originally created by @alienatorZ on GitHub (Dec 10, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13402 Originally assigned to: @jessegross on GitHub. ### What is the issue? I have Ubuntu 22.04 Ollama 0.13.3-rc0 with models like gpt-oss and qwen3 30ba3b I get: time=2025-12-10T01:05:16.820Z level=INFO source=server.go:1332 msg="llama runner started in 0.55 seconds" panic: caching disabled but unable to fit entire input in a batch goroutine 8 [running]: github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc00021d0e0, {0x0, {0x5d17aac04d30, 0xc000690100}, {0x5d17aac0f1a0, 0xc000011308}, {0xc0001e9908, 0x200, 0x25f}, {{0x5d17aac0f1a0, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:707 +0x1ac5 github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc00021d0e0, {0x5d17aabfa2a0, 0xc00036e0a0}) github.com/ollama/ollama/runner/ollamarunner/runner.go:460 +0x30b created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/ollamarunner/runner.go:1412 +0x4c9 [GIN] 2025/12/10 - 01:05:16 | 400 | 662.671261ms | 127.0.0.1 | POST "/v1/embeddings" ggml_backend_cuda_device_get_memory device GPU-3db830a0-9e60-5a10-12d2-610d17f21eda utilizing NVML memory reporting free: 9562619904 total: 25769803776 ggml_backend_cuda_device_get_memory device GPU-9d2aa8d9-e445-799f-a8e6-8613d292be49 utilizing NVML memory reporting free: 9516482560 total: 25769803776 time=2025-12-10T01:10:16.523Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 39367" time=2025-12-10T01:10:16.902Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 45263" time=2025-12-10T01:10:17.386Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41443" time=2025-12-10T01:10:17.637Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40973" time=2025-12-10T01:10:17.887Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41359" time=2025-12-10T01:10:18.137Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40929" time=2025-12-10T01:10:18.387Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 44135" time=2025-12-10T01:10:18.637Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40651" time=2025-12-10T01:10:18.887Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 44351" time=2025-12-10T01:10:19.137Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37923" time=2025-12-10T01:10:19.387Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46833" time=2025-12-10T01:10:19.637Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42845" time=2025-12-10T01:10:19.887Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40909" time=2025-12-10T01:10:20.137Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 39489" time=2025-12-10T01:10:20.387Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41233" time=2025-12-10T01:10:20.637Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40639" time=2025-12-10T01:10:20.887Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41111" time=2025-12-10T01:10:21.137Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 43361" time=2025-12-10T01:10:21.387Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40575" time=2025-12-10T01:10:21.636Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37059" time=2025-12-10T01:10:21.887Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41903" time=2025-12-10T01:10:22.137Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37109" time=2025-12-10T01:10:22.138Z level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout" time=2025-12-10T01:10:22.138Z level=WARN source=runner.go:356 msg="unable to refresh free memory, using old values" [GIN] 2025/12/10 - 02:11:11 | 200 | 40.105µs | 127.0.0.1 | GET "/api/version" ### Relevant log output ```shell ``` ### OS Ubuntu 22.04 ### GPU Nvidia Tesla P40 X2 ### CPU _No response_ ### Ollama version 0.13.3-rc0
GiteaMirror added the bug label 2026-04-22 18:19:44 -05:00
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#34610
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?