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

[PD Disaggregation] Support PD deployment of DeepSeekv3. (#5251)

Browse Source 
* Support deepseekv3 cache transfer for PD deploy

* clean some log info

---------

Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com”>
This commit is contained in:
K11OntheBoat
2025-12-02 14:11:50 +08:00
committed by GitHub
parent 117980dd4e
commit 2e1680838f
17 changed files with 620 additions and 400 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
fastdeploy/engine/engine.py
View File

@@ -755,8 +755,9 @@ class LLMEngine:
local_data_parallel_size=self.cfg.parallel_config.data_parallel_size,
)
)
ctx = multiprocessing.get_context("spawn")
self.dp_processed.append(
multiprocessing.Process(
ctx.Process(
target=start_data_parallel_service,
args=(
self.cfg,