xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-16 23:17:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

precommit

Browse Source 
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
This commit is contained in:
Tyler Michael Smith 2025-06-20 14:41:20 +00:00
parent 26fd8ca33c
commit 7a821f0e7f
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/model_executor/layers/fused_moe/layer.py
View File

@ -380,6 +380,7 @@ class FusedMoEMethodBase(QuantizeMethodBase):
# Note : We may want to use FP8 dispatch even otherwise just to
# reduce datamovement
assert act_quant_block_size is not None
use_fp8_dispatch = (quant_dtype == current_platform.fp8_dtype()
and act_quant_block_size[1]
== DEEPEP_QUANT_BLOCK_SIZE)