apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 09:07:10 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[feat] support prefix cache clearing when /clear_load_weight is called (#4008)

Browse Source 
* [feat] support clearing prefix cache (cherry-picked from release/2.1)

* [fix] fix ipc suffix, use port instead

* [fix] fix prefix caching not enabled

* [fix] fix key/value_cache_scales indent

* [fix] fix ep group all-reduce

* [fix] fix clear/update lock not working when workers > 1

* [chore] add preemption triggered info log

* [fix] fix code style

* [fix] fix max_num_seqs config

* [fix] do not force enable_prefix_caching=False in dynamic loading

* [fix] fix ci

* Revert "[fix] fix ci"

This reverts commit 0bc6d55cc8.

* [fix] initialize available_gpu_block_num with max_gpu_block_num

* [fix] fix config splitwise_role

* [fix] fix clearing caches synchronization and add more logs

* [chore] print cache_ready_signal in log

* [fix] fix scheduler_config.splitwise_role

* [fix] fix cache_messager cache_ready_signal create=True

* [fix] stop cache messager from launching in mixed deployment
This commit is contained in:
李泳桦
2025-09-28 19:42:53 +08:00
committed by GitHub
parent 59313ed7f9
commit 6265f4385f
20 changed files with 697 additions and 213 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/envs.py
View File

@@ -116,6 +116,8 @@ environment_variables: dict[str, Callable[[], Any]] = {
# Max pre-fetch requests number in PD
"FD_EP_MAX_PREFETCH_TASK_NUM": lambda: int(os.getenv("FD_EP_MAX_PREFETCH_TASK_NUM", "8")),
"FD_ENABLE_MODEL_LOAD_CACHE": lambda: bool(int(os.getenv("FD_ENABLE_MODEL_LOAD_CACHE", "0"))),
# Whether to clear cpu cache when clearing model weights.
"FD_ENABLE_SWAP_SPACE_CLEARING": lambda: int(os.getenv("FD_ENABLE_SWAP_SPACE_CLEARING", "0")),
}