Skip to content

[Feature]Supports FastDeploy using PFCC DeepGemm on architectures other than sm100. #6990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
chang-wenbin wants to merge 2 commits into
base: develop
Choose a base branch
from
+5 −2
Open

[Feature]Supports FastDeploy using PFCC DeepGemm on architectures other than sm100. #6990

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b6e4471
supportFD use PFCC DeepGemm
chang-wenbin Mar 24, 2026
b62c707
update deepgemm_whl
chang-wenbin Mar 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions fastdeploy/model_executor/layers/quantization/fp8_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,8 +80,10 @@ def load_deep_gemm():

logger.info("Detected sm100, use PFCC DeepGEMM")
else:
logger.info("use FastDeploy DeepGEMM")
import fastdeploy.model_executor.ops.gpu.deep_gemm as deep_gemm
paddle.enable_compat(scope={"deep_gemm"})
import deep_gemm as deep_gemm

logger.info("Use PFCC DeepGEMM")
else:
deep_gemm = None
return deep_gemm
Expand Down
1 change: 1 addition & 0 deletions requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,4 +49,5 @@ py-cpuinfo
flashinfer-python-paddle
flash_mask @ https://paddle-qa.bj.bcebos.com/ernie/flash_mask-4.0.post20260128-py3-none-any.whl
arctic_inference @ https://paddle-qa.bj.bcebos.com/ernie/arctic_inference-0.1.3-cp310-cp310-linux_x86_64.whl
deep-gemm-cpp @ https://paddle-qa.bj.bcebos.com/ernie/deep_gemm_cpp-2.2.0%2Blocal-cp310-cp310-linux_x86_64.whl
transformers>=4.55.1,<5.0.0
Loading