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 (#3284)

Browse Source 
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: YUNSHEN XIE <1084314248@qq.com>
This commit is contained in:
ming1753
2025-08-12 00:40:45 +08:00
committed by GitHub
parent 2fe31c6f0f
commit 9b07f85f6d
2 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
fastdeploy/engine/sched/resource_manager_v1.py
View File

@@ -195,7 +195,6 @@ class ResourceManagerV1(ResourceManager):
) )
request.num_image_end = img_num_per_boundary[new_boundary_idx] request.num_image_end = img_num_per_boundary[new_boundary_idx]
request.num_image_end = img_num_per_boundary[new_boundary_idx]
request.image_type_ids_start = np.sum(grid_thw[: request.num_image_start, 0]) request.image_type_ids_start = np.sum(grid_thw[: request.num_image_start, 0])
request.image_type_ids_end = np.sum(grid_thw[: request.num_image_end, 0]) request.image_type_ids_end = np.sum(grid_thw[: request.num_image_end, 0])
request.image_start = np.sum(np.prod(grid_thw[: request.num_image_start], axis=1)) request.image_start = np.sum(np.prod(grid_thw[: request.num_image_start], axis=1))

6
fastdeploy/worker/worker_process.py
View File

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