apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 00:57:33 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Bug Fix] fix vl V1 schedule bug (#3323)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* [Bug Fix] fix vl V1 schedule bug

* fix format
This commit is contained in:
ming1753
2025-08-12 11:31:39 +08:00
committed by GitHub
parent b808c49585
commit f5164215be
2 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
fastdeploy/worker/worker_process.py
View File

@@ -24,6 +24,7 @@ import paddle
import paddle.distributed as dist
from paddle.distributed import fleet
from fastdeploy import envs
from fastdeploy.config import (
CacheConfig,
DecodingConfig,
@@ -289,8 +290,9 @@ class PaddleDisWorkerProc:
if self.local_rank % mp_num_per_node == 0:
if self.task_queue.num_tasks() > 0:
# VL only support 1 batch to prefill
if not self.fd_config.model_config.enable_mm or not self.worker.exist_prefill():
if envs.ENABLE_V1_KVCACHE_SCHEDULER or not (
self.fd_config.model_config.enable_mm and self.worker.exist_prefill()
):
if self.nnode > 1 and self.parallel_config.tensor_parallel_size > self.max_chips_per_node:
self.task_queue.read_finish_flag.set(1)
else: