apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

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

5
fastdeploy/engine/engine.py
View File

@@ -286,7 +286,7 @@ class LLMEngine:
if request.get("stop_seqs_len") is not None:
stop_seqs_len = request.get("stop_seqs_len")
max_stop_seqs_num = int(envs.FD_MAX_STOP_SEQS_NUM)
max_stop_seqs_num = envs.FD_MAX_STOP_SEQS_NUM
if len(stop_seqs_len) > max_stop_seqs_num:
error_msg = (
f"Length of stop ({stop_seqs_len}) exceeds the limit max_stop_seqs_num({max_stop_seqs_num})."
@@ -294,7 +294,7 @@ class LLMEngine:
)
llm_logger.error(error_msg)
raise EngineError(error_msg, error_code=400)
stop_seqs_max_len = int(envs.FD_STOP_SEQS_MAX_LEN)
stop_seqs_max_len = envs.FD_STOP_SEQS_MAX_LEN
for single_stop_seq_len in stop_seqs_len:
if single_stop_seq_len > stop_seqs_max_len:
error_msg = (
@@ -568,6 +568,7 @@ class LLMEngine:
"disable_any_whitespace": self.cfg.structured_outputs_config.disable_any_whitespace,
"disable_custom_all_reduce": self.cfg.parallel_config.disable_custom_all_reduce,
"use_internode_ll_two_stage": self.cfg.parallel_config.use_internode_ll_two_stage,
"disable_sequence_parallel_moe": self.cfg.parallel_config.disable_sequence_parallel_moe,
"enable_logprob": self.cfg.model_config.enable_logprob,
"lm_head_fp32": self.cfg.model_config.lm_head_fp32,
}