frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Expand SUPPORTED_HIDDEN_SIZES for DeepEP low-latency kernels (#21818)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li
2025-07-31 11:41:12 +08:00
committed by GitHub
parent 61445453df
commit 0f7919fca0
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py
View File

@ -40,7 +40,7 @@ class DeepEPLLPrepareAndFinalize(mk.FusedMoEPrepareAndFinalize):
# DeepEP low-latency kernels are compiled only for certain
# specific hidden sizes.
SUPPORTED_HIDDEN_SIZES = [2048, 2560, 4096, 5120, 7168]
SUPPORTED_HIDDEN_SIZES = [2048, 2560, 4096, 5120, 6144, 7168]
def __init__(self,
buffer: deep_ep.Buffer,