Wenbo Ji 嵇文博
b7bd7775ed
[perf] Default SM100 long-sequence Attn-QAT tiling ( #1899 )
...
On SM100, the Attn-QAT training kernel now uses a faster route for non-causal
BF16 attention with equal query and key lengths of 16384 tokens or more. The
forward pass processes full KV tiles without bounds masks, and a separate masked
step handles the partial tail tile. The backward pass uses 64x128 dQ and dK/dV
tiles. Outputs, softmax statistics and all gradients are bitwise identical to the
previous route. FASTVIDEO_ATTN_QAT_SM100_OPTIMIZED=0 turns off the SM100 route,
and FASTVIDEO_ATTN_QAT_SM100_WIDE_BWD=0 keeps the 64x64 backward tiles.
On GB200 with 6 heads and 31200 tokens, the forward kernel time goes from 9.14 ms
to 6.96 ms and the backward kernel time from 17.41 ms to 15.85 ms.
2026-10-07 15:14:38 -07:00
Yogya Mehrotra
017ce6602d
[bugfix] Fix dead NVFP4 QAT plumbing: bench imports, int8 error string, smooth_q crash ( #1723 )
2026-09-24 17:09:33 -07:00
Raghav K
b2062556a9
[perf] VSA Triton: widen the autotune num_stages range (the optimum was outside it) ( #1706 )
2026-08-26 12:30:56 -07:00
William Lin and Claude Fable 5
56d4a6074f
[bugfix] fastvideo-kernel: fix Triton block-sparse backward logit scaling (bf16 K pre-scaling) ( #1730 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com >
2026-08-21 04:50:06 -05:00
William Lin
9028953625
[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version ( #1702 )
2026-08-08 22:24:17 -07:00
9709b7513b
[feat] Port NVFP4 QAT/QAD to modular train framework ( #1619 )
...
Co-authored-by: Peiyuan Zhang <email>
Co-authored-by: Peiyuan <a>
2026-07-18 15:01:09 -07:00
xsank and mergify[bot]
31b719ae49
[perf] optimize compress & topk kernel ( #1421 )
...
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-23 18:51:22 +00:00
eed9c4bfbf
[kernel] QAD 5090: Add Attn-QAT training Triton kernels (11/12) ( #1460 )
...
Co-authored-by: William Lin <SolitaryThinker@users.noreply.github.com >
Co-authored-by: Loay Rashid <42599591+loaydatrain@users.noreply.github.com >
Co-authored-by: Kaiqin Kong <k1kong@ucsd.edu >
2026-06-17 13:35:12 -07:00
Mook
7b872cc41e
[Perf] Skip bool-mask round-trip in block-sparse VSA attention ( #1243 )
2026-04-26 15:14:37 -07:00
alexzms
d925ad05f3
[bugfix] fastvideo-kernel: fix VSA Triton padding NaNs and support q/kv length mismatch ( #1094 )
2026-02-13 12:39:49 -08:00
Loay Rashid
dea69cf651
[New Model] Turbodiffusion ( #971 )
2026-01-02 17:55:56 -06:00
RoyWang and roywang
de264fcc99
[fix]: fix STA trition kernel for AMD RDNA archs ( #969 )
...
Co-authored-by: roywang <roywang@amd.com >
2025-12-29 14:25:32 -06:00
William Lin and ShreejithSG
2f6230abcf
[kernel] Reorg and fix fastvideo-kernel ( #962 )
...
Co-authored-by: ShreejithSG <shreejithsg@gmail.com >
2025-12-26 01:50:24 -06:00
Wenbo Ji 嵇文博