[Bug Fix] fix vl V1 schedule bug (#3323)

* [Bug Fix] fix vl V1 schedule bug

* fix format

Author: ming1753

fastdeploy/engine/sched/resource_manager_v1.py

@@ -195,7 +195,6 @@ def _get_num_new_tokens(self, request, token_budget):
                 )
                 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_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))

fastdeploy/worker/worker_process.py

@@ -24,6 +24,7 @@
 import paddle.distributed as dist
 from paddle.distributed import fleet
 
+from fastdeploy import envs
 from fastdeploy.config import (
     CacheConfig,
     DecodingConfig,
@@ -289,8 +290,9 @@ def event_loop_normal(self) -> None:
             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: