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

enhance set_stop_value_multi_ends and standardize the registration of some operators (#4525)

Browse Source 
* fix custom_ops

* paddleformers>=0.3.1
This commit is contained in:
Yuanle Liu
2025-10-21 22:06:06 +08:00
committed by GitHub
parent dc7facaa7f
commit 3b58310c26
18 changed files with 68 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
fastdeploy/engine/engine.py
View File

@@ -426,7 +426,6 @@ class LLMEngine:
"ENABLE_FASTDEPLOY_LOAD_MODEL_CONCURRENCY": 0,
"LOAD_STATE_DICT_THREAD_NUM": len(self.cfg.parallel_config.device_ids.split(",")),
"PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION": "python",
"FLAGS_use_append_attn": 1,
"NCCL_ALGO": "Ring",
"FLAGS_max_partition_size": int(os.getenv("FLAGS_max_partition_size", 1024)),
}