apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 08:16:42 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

support w4afp8 EP inference (#3044)
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
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Yuan Xiaolan
2025-08-25 11:27:45 +08:00
committed by GitHub
parent 46664985fc
commit 9205c88da1
17 changed files with 995 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
custom_ops/gpu_ops/cpp_extensions.cc
View File

@@ -192,7 +192,8 @@ paddle::Tensor MoeExpertFFNFunc(
const paddle::optional<paddle::Tensor>& down_proj_scale,
const paddle::optional<paddle::Tensor>& down_proj_in_scale,
const paddle::optional<paddle::Tensor>& expert_idx_per_token,
const std::string& quant_method, const bool used_in_ep_low_latency);
const std::string& quant_method, const bool used_in_ep_low_latency,
const int estimate_total_token_nums);
paddle::Tensor MoeExpertFFNWint2Func(
const paddle::Tensor& permute_input,