apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 00:33:03 +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

2
fastdeploy/model_executor/models/deepseek_v3.py
View File

@@ -116,6 +116,7 @@ class DeepSeekV3MoE(nn.Layer):
super().__init__()
self.tp_size = fd_config.parallel_config.tensor_parallel_size
self.norm_topk_prob = fd_config.model_config.norm_topk_prob
weight_key_map = {
"gate_correction_bias_key": f"{prefix}.gate.e_score_correction_bias",
@@ -145,6 +146,7 @@ class DeepSeekV3MoE(nn.Layer):
self.experts = FusedMoE(
fd_config=fd_config,
reduce_results=False,
renormalize=self.norm_topk_prob,
moe_intermediate_size=fd_config.model_config.moe_intermediate_size,
num_experts=fd_config.model_config.n_routed_experts,
top_k=fd_config.model_config.num_experts_per_tok,