分支列表

默认分支

0ba6b6aab7 · perf(mla): add opt-in packed Q decode for FP8 and FP16 (#1512) · 最后更新于 2026-09-12 09:04:01 +00:00

分支列表

2d497754ff · ci(glm53): lower memory ratio for scheduler stress · 最后更新于 2026-09-08 00:56:55 +00:00    frostbyte_neo

83
3

3f5a77fcbd · refactor(scheduler): judge the retraction exemption by the admission-time budget · 最后更新于 2026-09-07 18:04:31 +00:00    frostbyte_neo

83
2

56ef6eb1ff · ci(glm53): lower memory ratio for scheduler stress · 最后更新于 2026-09-07 17:31:40 +00:00    frostbyte_neo

83
1

fe78df0b8d · ci(glm53): lower memory ratio for scheduler stress · 最后更新于 2026-09-07 17:31:40 +00:00    frostbyte_neo

83
2

4fdbbae6f3 · refactor(scheduler): a State cache group is the checkpoint shape · 最后更新于 2026-09-07 17:18:13 +00:00    frostbyte_neo

83
4

cb7597c7c9 · fix(autotune): preserve eager phase during decode tuning · 最后更新于 2026-09-07 17:14:54 +00:00    frostbyte_neo

82
6

770a204a23 · feat(qsa): support TP1 and TP2 CuTe head groups · 最后更新于 2026-09-07 12:51:25 +00:00    frostbyte_neo

83
3

92afe1de8a · Merge branch 'main' into k3-latent-down-column-shard · 最后更新于 2026-09-07 04:59:38 +00:00    frostbyte_neo

83
30

9b457ac036 · deps: update Triton/Proton to post20260906 · 最后更新于 2026-09-06 21:35:40 +00:00    frostbyte_neo

89
1

b0bdf623dc · fix: preserve TRTLLM draft prefill metadata during decode refresh · 最后更新于 2026-09-06 19:27:53 +00:00    frostbyte_neo

89
1

cb61c23ed0 · Update TokenSpeed Triton vendor release · 最后更新于 2026-09-06 17:20:53 +00:00    frostbyte_neo

89
9

afdd2c2a1f · Merge branch 'main' into unify-state-growth-reserve · 最后更新于 2026-09-06 04:22:50 +00:00    frostbyte_neo

89
3

58b28b20ad · Merge origin/main into borontion/fix-mi450-sim-runtime · 最后更新于 2026-09-05 23:43:24 +00:00    frostbyte_neo

91
5

1a082199e7 · test(ci): pin EvalScope for Kimi K3 diagnosis · 最后更新于 2026-09-05 16:46:03 +00:00    frostbyte_neo

104
1

7a41647396 · ci(amd): isolate ed6 Kimi-K3 comparison · 最后更新于 2026-09-04 10:10:12 +00:00    frostbyte_neo

100
3

9a89f877b0 · fix(qsa): require metadata capacity explicitly · 最后更新于 2026-09-04 10:09:54 +00:00    frostbyte_neo

99
10

c0f0b49f17 · test(amd): isolate gdot reduction output buffer · 最后更新于 2026-09-04 10:04:29 +00:00    frostbyte_neo

104
3

237a5928e5 · ci(amd): isolate Kimi-K3 reduction fix validation · 最后更新于 2026-09-04 09:05:02 +00:00    frostbyte_neo

99
2

a507b430dd · test(amd): isolate gdot reduction output buffer · 最后更新于 2026-09-04 08:58:36 +00:00    frostbyte_neo

107
4

3cef620d26 · ci(amd): isolate Kimi-K3 Eagle3 fix validation · 最后更新于 2026-09-04 08:39:20 +00:00    frostbyte_neo

99
2