 Kaixi
|
f3225bceb3
|
[DSV4] Emit TMA-aligned UE8M0 scales for FP8 einsum (#34277)
|
2026-08-16 22:06:41 -07:00 |
|
|
|
a0a76e4485
|
[DSV4] perf: Enable alt stream during BCG prefill (#29070)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
|
2026-08-11 05:10:19 -07:00 |
|
|
Kaixi
|
6c05aaae7e
|
[trtllm_mha] perf: Stop allocating per-layer scratch inside the decode CUDA graph (#33063)
|
2026-08-04 19:27:26 -07:00 |
|
|
Kaixi
|
dc0b3eb68f
|
[2/3] [EAGLE] perf: Fuse TP vocab-parallel embedding (#30948)
|
2026-07-16 15:57:51 -07:00 |
|
|
Kaixi
|
d539bf2cda
|
[1/3] [EAGLE] perf: Fuse topk=1 draft postprocess (#30947)
|
2026-07-16 15:57:27 -07:00 |
|
|
Kaixi
|
9f2bc24b35
|
Fix/dsv4 flash eagle dummy ima (#25892)
|
2026-05-20 15:41:28 -07:00 |
|
|
Kaixi
|
744b1c9e6f
|
Added fallback to individual copy_ (#20683)
|
2026-03-17 14:44:38 -07:00 |
|
|
Kaixi
|
8c5ca37aef
|
Batch copy_ with torch._foreach_copy_ (#18558)
|
2026-03-08 19:09:02 -07:00 |
|
|
Kaixi
|
98ad284ebf
|
Added cuda availability guard (#18480)
|
2026-02-13 20:18:34 +08:00 |
|
|
Kaixi
|
2b2515423a
|
Skipped warning on sm100 (#18000)
|
2026-01-31 20:21:03 -08:00 |
|