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 #9332] Flash Attention Enabled Incorrectly Due to Fallback in Head Count Metadata #52604

New Issue
Open
opened 2026-04-28 23:50:06 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-28 23:50:06 -05:00
Owner
Copy Link

Originally created by @ItzCrazyKns on GitHub (Feb 25, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9332

What is the issue?

When loading a model that lacks metadata for attention.key_length and attention.value_length, the fallback mechanism in the kv.Uint function returns the embedding head count for both fields. This causes the check in SupportsFlashAttention(), which compares the key and value head counts, to show success incorrectly (since both values are identical), even if the model does not truly support Flash Attention. As a result, Flash Attention is enabled, leading to issues such as segmentation faults (e.g., SIGSEGV in llama/ggml-cuda/fattn.cu:67).

Steps to Reproduce:

  1. Load a model that does not include attention.key_length and attention.value_length in its metadata.
  2. Observe that the functions EmbeddingHeadCountK() and EmbeddingHeadCountV() fallback to the embedding head count.
  3. The SupportsFlashAttention() method then compares these equal values and incorrectly concludes that the model supports Flash Attention.
  4. Enabling Flash Attention under these conditions leads to crashes (segmentation faults).

Expected Behavior:
If the model metadata is missing attention.key_length and attention.value_length, the server should disable Flash Attention by default.

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @ItzCrazyKns on GitHub (Feb 25, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9332 ### What is the issue? When loading a model that lacks metadata for `attention.key_length` and `attention.value_length`, the fallback mechanism in the `kv.Uint` function returns the embedding head count for both fields. This causes the check in `SupportsFlashAttention()`, which compares the key and value head counts, to show success incorrectly (since both values are identical), even if the model does not truly support Flash Attention. As a result, Flash Attention is enabled, leading to issues such as segmentation faults (e.g., SIGSEGV in `llama/ggml-cuda/fattn.cu:67`). **Steps to Reproduce:** 1. Load a model that does not include `attention.key_length` and `attention.value_length` in its metadata. 2. Observe that the functions `EmbeddingHeadCountK()` and `EmbeddingHeadCountV()` fallback to the embedding head count. 3. The `SupportsFlashAttention()` method then compares these equal values and incorrectly concludes that the model supports Flash Attention. 4. Enabling Flash Attention under these conditions leads to crashes (segmentation faults). **Expected Behavior:** If the model metadata is missing `attention.key_length` and `attention.value_length`, the server should disable Flash Attention by default. ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-28 23:50:06 -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#52604
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?