vulkan: fix rms_norm+mul fusion #14545
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
The fused operation was grabbing the epsilon value from the wrong place. Add an env var to disable fusion. Add some missing checks for supported shapes/types. Handle fused rms_norm+mul in check_results.
github-actions
bot
added
testing
|
These changes fix both Mistral 7b at Q8 and the spaces issue with Mistral 3.2 at Q3_K_L. Thank you! |
Does it also fix the other model issues you mentioned (Mamba something)? |
0cc4m
approved these changes
Jul 6, 2025
Unfortunately, I've already deleted that model since it wasn't very stable in general (doesn't stop properly on short responses even on very low temperature), regardless of backend. I'll have to look at a better Mamba-based model to test it properly. |
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
Jul 7, 2025
* origin/master: CUDA: add bf16 and i32 to getrows (ggml-org#14529) vulkan: increase LOAD_VEC_A to 8 (IQ1/IQ2) or 4 (IQ3) (ggml-org#14485) vulkan: fix rms_norm+mul fusion (ggml-org#14545) vulkan: Handle updated FA dim2/3 definition (ggml-org#14518) server : fix assistant prefilling when content is an array (ggml-org#14360) opencl: add GELU_ERF (ggml-org#14476) eval-callback : check for empty input (ggml-org#14539) test-backend-ops: add support for specifying output format (ggml-org#14368) metal : disable fast math in all quantize kernels (ggml-org#14528) batch : add optional for sequential equal split (ggml-org#14511) graph : prepare for 4D mask (ggml-org#14515) batch : add n_used count (ggml-org#14512) CANN: Replace aclrtMemsetSync with aclnnInplaceZero operator (ggml-org#14002) ggml : implement GEGLU_ERF and GEGLU_QUICK ops (ggml-org#14445)
qnixsynapse
pushed a commit
to menloresearch/llama.cpp
that referenced
this pull request
Jul 10, 2025
The fused operation was grabbing the epsilon value from the wrong place. Add an env var to disable fusion. Add some missing checks for supported shapes/types. Handle fused rms_norm+mul in check_results.
qnixsynapse
pushed a commit
to menloresearch/llama.cpp
that referenced
this pull request
Jul 10, 2025
The fused operation was grabbing the epsilon value from the wrong place. Add an env var to disable fusion. Add some missing checks for supported shapes/types. Handle fused rms_norm+mul in check_results.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The fused operation was grabbing the epsilon value from the wrong place.
Add an env var to disable fusion.
Add some missing checks for supported shapes/types.
Handle fused rms_norm+mul in check_results.
Fixes #14540.