opencl: fix fused RMS norm mul view offset#26085
Open
happyyzy wants to merge 1 commit into
ggml-org:masterggml-org/llama.cpp:masterfrom
happyyzy:agent/opencl-fix-rms-norm-mul-view-offsethappyyzy/llama.cpp:agent/opencl-fix-rms-norm-mul-view-offsetCopy head branch name to clipboard
Open
opencl: fix fused RMS norm mul view offset#26085happyyzy wants to merge 1 commit intoggml-org:masterggml-org/llama.cpp:masterfrom happyyzy:agent/opencl-fix-rms-norm-mul-view-offsethappyyzy/llama.cpp:agent/opencl-fix-rms-norm-mul-view-offsetCopy head branch name to clipboard
happyyzy wants to merge 1 commit into
ggml-org:masterggml-org/llama.cpp:masterfrom
happyyzy:agent/opencl-fix-rms-norm-mul-view-offsethappyyzy/llama.cpp:agent/opencl-fix-rms-norm-mul-view-offsetCopy head branch name to clipboard
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
This change fixes an incorrect input address in the fused OpenCL RMS_NORM -> MUL path.
The offset for the second multiplication input, src1, was incorrectly calculated using src0->view_offs. It now correctly uses src1->view_offs.