Fix a wrong reference to seqlen_k variable in the varlen kernel #1192
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Outdated suggestions cannot be applied.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.
This fixes a line in
compute_attn_1rowblock_splitkv
kernel function that usesparams.seqlen_k
to usebinfo.actual_seqlen_k
instead to access the seqlen_k value.This is a fix to the
flash_attn_varlen_func
function producing wrong results when used with cudaGraph over different input parameters, as found in the vLLM repo (vllm-project/vllm#6052).