Skip to content

GitLab

Unverified Commit 0f7919fc authored by Jee Jee Li's avatar Jee Jee Li Committed by GitHub
Browse files

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


Signed-off-by: default avatarJee Jee Li <pandaleefree@gmail.com>
parent 61445453
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py
View file @ 0f7919fc
...@@ -40,7 +40,7 @@ class DeepEPLLPrepareAndFinalize(mk.FusedMoEPrepareAndFinalize): ...@@ -40,7 +40,7 @@ class DeepEPLLPrepareAndFinalize(mk.FusedMoEPrepareAndFinalize):
# DeepEP low-latency kernels are compiled only for certain # DeepEP low-latency kernels are compiled only for certain
# specific hidden sizes. # specific hidden sizes.
SUPPORTED_HIDDEN_SIZES = [2048, 2560, 4096, 5120, 7168] SUPPORTED_HIDDEN_SIZES = [2048, 2560, 4096, 5120, 6144, 7168]
def __init__(self, def __init__(self,
buffer: deep_ep.Buffer, buffer: deep_ep.Buffer,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment