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 #10262] key not found Warnings in Logs When Running Gemma3 12B on AMD EPYC #32496

New Issue
Closed
opened 2026-04-22 13:49:07 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 13:49:07 -05:00
Owner
Copy Link

Originally created by @bhargav-11 on GitHub (Apr 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10262

What is the issue?

What is the issue?
When running the gemma3 12b model on a machine with an AMD EPYC 9000 series CPU, Ollama serve logs repeatedly show "key not found" warnings. These keys appear to relate to tokenizer and model-specific configuration options. Despite these warnings, the model seems to load and run without crashing, but I'm unsure if this indicates missing functionality, fallback behavior, or misconfiguration.

Expected behavior
I expected the model to initialize cleanly without warnings, assuming it is fully compatible with Ollama and the current runtime setup.

Relevant log output

time=2025-04-14T09:58:54.221Z level=INFO source=ggml.go:289 msg="model weights" buffer=CPU size="8.3 GiB"
time=2025-04-14T09:58:54.364Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model"
time=2025-04-14T09:58:54.512Z level=INFO source=ggml.go:388 msg="compute graph" backend=CPU buffer_type=CPU
time=2025-04-14T09:58:54.513Z level=WARN source=ggml.go:152 msg="key not found" key=tokenizer.ggml.add_eot_token default=false
time=2025-04-14T09:58:54.519Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.attention.layer_norm_rms_epsilon default=9.999999974752427e-07
time=2025-04-14T09:58:54.519Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.local.freq_base default=10000
time=2025-04-14T09:58:54.519Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.global.freq_base default=1e+06
time=2025-04-14T09:58:54.519Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.freq_scale default=1
time=2025-04-14T09:58:54.519Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.mm_tokens_per_image default=256
time=2025-04-14T09:58:54.615Z level=INFO source=server.go:619 msg="llama runner started in 0.50 seconds"

OS

Linux

GPU

No response

CPU

AMD

Ollama version

0.6.5

Originally created by @bhargav-11 on GitHub (Apr 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10262 ### What is the issue? What is the issue? When running the gemma3 12b model on a machine with an AMD EPYC 9000 series CPU, Ollama serve logs repeatedly show "key not found" warnings. These keys appear to relate to tokenizer and model-specific configuration options. Despite these warnings, the model seems to load and run without crashing, but I'm unsure if this indicates missing functionality, fallback behavior, or misconfiguration. Expected behavior I expected the model to initialize cleanly without warnings, assuming it is fully compatible with Ollama and the current runtime setup. ### Relevant log output ```shell time=2025-04-14T09:58:54.221Z level=INFO source=ggml.go:289 msg="model weights" buffer=CPU size="8.3 GiB" time=2025-04-14T09:58:54.364Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" time=2025-04-14T09:58:54.512Z level=INFO source=ggml.go:388 msg="compute graph" backend=CPU buffer_type=CPU time=2025-04-14T09:58:54.513Z level=WARN source=ggml.go:152 msg="key not found" key=tokenizer.ggml.add_eot_token default=false time=2025-04-14T09:58:54.519Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.attention.layer_norm_rms_epsilon default=9.999999974752427e-07 time=2025-04-14T09:58:54.519Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.local.freq_base default=10000 time=2025-04-14T09:58:54.519Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.global.freq_base default=1e+06 time=2025-04-14T09:58:54.519Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.freq_scale default=1 time=2025-04-14T09:58:54.519Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.mm_tokens_per_image default=256 time=2025-04-14T09:58:54.615Z level=INFO source=server.go:619 msg="llama runner started in 0.50 seconds" ``` ### OS Linux ### GPU _No response_ ### CPU AMD ### Ollama version 0.6.5
GiteaMirror added the bug label 2026-04-22 13:49:07 -05:00
GiteaMirror commented 2026-04-22 13:49:10 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 14, 2025):

The model is missing a few KV entries. ollama uses defaults. There's no issue here.

<!-- gh-comment-id:2801231758 --> @rick-github commented on GitHub (Apr 14, 2025): The model is missing a few KV entries. ollama uses defaults. There's no issue here.
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#32496
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?