xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-23 02:45:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix precommit fail in fused_moe intermediate_cache2 chunking (#13772)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin 2025-02-24 12:25:47 -05:00 committed by GitHub
parent 227578480d
commit db986c19ea
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/layers/fused_moe/fused_moe.py
View File

@ -1271,7 +1271,8 @@ def fused_experts_impl(hidden_states: torch.Tensor,
# so the cache size and config are already set correctly and
# do not need to be adjusted.
intermediate_cache1 = intermediate_cache1[:tokens_in_chunk]
intermediate_cache2 = intermediate_cache2[:tokens_in_chunk * topk_ids.shape[1]]
intermediate_cache2 = intermediate_cache2[:tokens_in_chunk *
topk_ids.shape[1]]
intermediate_cache3 = intermediate_cache3[:tokens_in_chunk]
config = get_config_func(tokens_in_chunk)