apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Fix noaux_tc cuda Error 700 in CUDAGraph and Add wfp8apf8 moe quant method (#4115)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details

Browse Source 
* improve per_token_quant_fp8 performance

* support moe wfp8apf8

* check glm test

* fix noaux_tc op in cudagraph, support noaux_tc return the correct

* check

* check inf and overwrite score in noaux_tc

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
chen
2025-09-22 21:27:37 +08:00
committed by GitHub
parent 6b47773bd6
commit f38b174a75
17 changed files with 924 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
fastdeploy/model_executor/layers/quantization/wfp8afp8.py
View File

@@ -23,6 +23,7 @@ from fastdeploy.model_executor.layers.linear import (
MergedColumnParallelLinear,
QKVParallelLinear,
)
from fastdeploy.model_executor.layers.moe import FusedMoE
from fastdeploy.model_executor.layers.quantization.ops import (
cutlass_scaled_mm,
scaled_fp8_quant,
@@ -66,7 +67,14 @@ class WFP8AFP8Config(QuantConfigBase):
def get_quant_method(self, layer) -> Optional[QuantMethodBase]:
""" """
return WFP8AFP8LinearMethod(self)
if isinstance(layer, FusedMoE):
from fastdeploy.model_executor.layers.moe.fused_moe_triton_backend import (
Wfp8Afp8MoEMethod,
)
return Wfp8Afp8MoEMethod(self)
else:
return WFP8AFP8LinearMethod(self)
class WFP8AFP8LinearMethod(QuantMethodBase):