apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-21 15:49:31 +08:00
Code Issues Actions 6 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

4
fastdeploy/model_executor/layers/moe/moe.py
View File

@@ -66,6 +66,7 @@ def get_moe_scores(
top_k,
routed_scaling_factor,
e_score_correction_bias,
renormalize: bool = False,
) -> paddle.Tensor:
"""
compute moe scores using e_score_correction_bias.
@@ -79,6 +80,7 @@ def get_moe_scores(
n_group if n_group > 0 else 1,
topk_group if topk_group > 0 else 1,
top_k,
renormalize,
routed_scaling_factor,
)
return scores, topk_values, topk_idx
@@ -93,6 +95,7 @@ class FusedMoE(nn.Layer):
self,
fd_config,
reduce_results: bool = True,
renormalize: bool = False,
moe_intermediate_size: int = -1,
num_experts: int = -1,
expert_id_offset: int = 0,
@@ -119,6 +122,7 @@ class FusedMoE(nn.Layer):
self.fd_config = fd_config
self.layer_idx = layer_idx
self.reduce_results = reduce_results
self.renormalize = renormalize
self.tp_rank = fd_config.parallel_config.tensor_parallel_rank
self.tp_size = fd_config.parallel_config.tensor_parallel_size
self.ep_size = fd_config.parallel_config.expert_parallel_size