apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 17:17:14 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] Support batched tokens for EP (#3415)

Browse Source 
* Support batched tokens for EP

* Support batched tokens for EP

* Support batched tokens for EP

* Support batched tokens for EP

* Support batched tokens for EP and fix bug

* Support batched tokens for EP and fix bug

* Support batched tokens for EP and fix bug

* Support batched tokens for EP and fix bug
This commit is contained in:
chenjian
2025-08-18 11:43:36 +08:00
committed by GitHub
parent 3f86ae0007
commit aba94169dc
9 changed files with 235 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/output/token_processor.py
View File

@@ -270,7 +270,7 @@ class TokenProcessor:
self.resource_manager._recycle_block_tables(task)
if self.prefill_result_status[task_id] != "finished":
result.error_code = 400
result.error_message = f"{task_id} failed to {self.prefill_result_status[task_id]}"
result.error_msg = f"{task_id} failed to {self.prefill_result_status[task_id]}"
self.split_connector.send_first_token(task.disaggregate_info, [result])
del self.resource_manager.req_dict[task_id]
break