apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-24 01:29:57 +08:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

Revert "[Optimization] Optimize ttft for prefill pd (#6680)" (#7386)

Browse Source 
* Revert "[Optimization] Optimize ttft for prefill pd (#6680)"

This reverts commit 6727df8286.

* fix revert pr
This commit is contained in:
freeliuzc
2026-04-14 20:01:39 +08:00
committed by GitHub
parent 8a8beca548
commit f6c066fb9d
11 changed files with 135 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/usage/environment_variables.md
+3
View File
@@ -162,6 +162,9 @@ environment_variables: dict[str, Callable[[], Any]] = {
# Whether to enable the decode caches requests for preallocating resource
"FD_ENABLE_CACHE_TASK": lambda: os.getenv("FD_ENABLE_CACHE_TASK", "0"),
# Batched token timeout in EP
"FD_EP_BATCHED_TOKEN_TIMEOUT": lambda: float(os.getenv("FD_EP_BATCHED_TOKEN_TIMEOUT", "0.1")),
# Max pre-fetch requests number in PD
"FD_EP_MAX_PREFETCH_TASK_NUM": lambda: int(os.getenv("FD_EP_MAX_PREFETCH_TASK_NUM", "8")),