kvcache nz #1054
Closed
kvcache nz #1054
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
76 tasks
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
|
torch_npu.npu_fused_infer_attention_score only support K V with format of ND(https://www.hiascend.com/document/detail/zh/Pytorch/700/apiref/apilist/ptaoplist_001232.html). Does this PR require newer vision of torch_npu and CANN? |
return to use layout=BNSD in npu_fused_infer_attention_score when KV_NZ disabled
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
What this PR does / why we need it?
Enable kvcache_nz for the decode process in the graph mode, which reduces the time consumed by FA in long sequences.
Does this PR introduce any user-facing change?
If need to enable kvcache_nz, should set the environment variable VLLM_ENABLE_KV_NZ: "1"
How was this patch tested?
Tested in deepseek model, with batchsize 64 and seq_len 1k+3k: 61 layers FA total time 20.80ms -> 19.76ms