refactor linear attention backend (#18622)

Co-authored-by: yizhang2077 <1109276519@qq.com>
This commit is contained in:
Yuhao Yang
2026-02-25 23:02:44 +08:00
committed by GitHub
co-authored by yizhang2077
parent 471acd98b9
commit c7c4a1cbbd
14 changed files with 1453 additions and 843 deletions
-2
View File
@@ -185,8 +185,6 @@ class Envs:
SGLANG_GRAMMAR_MAX_POLL_ITERATIONS = EnvInt(10000)
SGLANG_DISABLE_OUTLINES_DISK_CACHE = EnvBool(False)
# CuTe DSL GDN Decode
SGLANG_USE_CUTEDSL_GDN_DECODE = EnvBool(False)
# Test & Debug
SGLANG_DETECT_SLOW_RANK = EnvBool(False)