minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[MoE] Retire the AOT moe_fused_gate / kimi_k2_moe_fused_gate gate kernels (#26771) (#29997)

Browse Source 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Xiaoyu Zhang
2026-07-07 13:53:17 +08:00
committed by GitHub
co-authored by Claude Opus 4.8
parent 9bd02dc5b9
commit 1da7d3a50b
19 changed files with 45 additions and 2499 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_dsv4.py
+2 -2
View File
@@ -68,7 +68,7 @@ class TestUnifiedDeepSeekV4FlashHiCache(UnifiedRadixTreeTestMixin, CustomTestCas
"--chunked-prefill-size",
"8192",
"--mem-fraction-static",
"0.9",
"0.92",
"--disable-shared-experts-fusion",
"--enable-hierarchical-cache",
"--hicache-ratio",
@@ -148,7 +148,7 @@ class TestUnifiedDeepSeekV4FlashHiCacheL3(AccuracyTwoPassMixin, CustomTestCase):
"--chunked-prefill-size",
"8192",
"--mem-fraction-static",
"0.9",
"0.92",
"--disable-shared-experts-fusion",
"--enable-hierarchical-cache",
"--hicache-ratio",