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

[Optimization] support mm prefill batch (#5313)
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 mm prefill batch

* update code

* update code

* update code

* update code

* fix encoder cache bug

* update code

* update code

* fix bug

* fix paddle ocr bug

* fix xpu bug

* update code
This commit is contained in:
kevin
2025-12-11 22:21:14 +08:00
committed by GitHub
parent 7116982995
commit 954a145d57
14 changed files with 769 additions and 296 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
fastdeploy/config.py
View File

@@ -241,6 +241,12 @@ class ModelConfig:
self._post_init()
def disable_mm_prefill_batch(self):
"""
check if the model architecture disable for mm prefill
"""
return self._architecture in ["Ernie5ForCausalLM"]
def _post_init(self):
self.is_unified_ckpt = check_unified_ckpt(self.model)
self.runner_type = self._get_runner_type(self.architectures, self.runner)
@@ -1618,7 +1624,7 @@ class FDConfig:
and self.model_config is not None
and self.model_config.enable_mm
):
self.max_prefill_batch = 1 # TODO:当前多模prefill阶段只支持并行度为1,待优化
self.max_prefill_batch = 1 # TODO:当前V0多模prefill阶段只支持并行度为1,待优化
else:
self.max_prefill_batch = self.scheduler_config.max_num_seqs