apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 21 Packages Projects Releases Wiki Activity

[TSP] Support qwen3 moe tsp + cudagraph (#4871)
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 
* support qwen3_moe tsp mode

* fix

* fix

* update

* update

* update

* fix

* support external_rmsnorm

* update

* fix
This commit is contained in:
Yuanle Liu
2025-11-10 23:37:51 +08:00
committed by GitHub
parent fb2eb403ab
commit 3dc0ffa46d
28 changed files with 173 additions and 273 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/model_executor/load_weight_utils.py
+1 -1
View File
@@ -269,7 +269,7 @@ def load_ep_checkpoint(cls: PretrainedModel, model_path: str, fd_config: FDConfi
if fd_config.parallel_config.tensor_parallel_size > 1:
no_tp_action_keys = copy.deepcopy(num_local_ffn_keys)
if fd_config.parallel_config.ep_tp_strategy == "all_to_all":
if fd_config.parallel_config.use_sequence_parallel_moe:
for i in range(fd_config.model_config.moe_layer_start_index, fd_config.model_config.num_hidden_layers):
k = f"ernie.layers.{i}.self_attn.o_proj.weight"
if k in weight_list: