10 Commits

Include renames

Author	SHA1	Message	Date
Will LinandClaude Fable 5	95f4f54712	[bugfix] Triton block-sparse backward: scale QK^T after the dot, keep K raw ... The backward pre-scaled K by sm_scale*log2(e) in bf16 before recomputing logits, so the recompute drifted from the forward's saved LSE proportionally to |logit|; exp2 amplifies that into exponentially wrong probabilities and garbage dK/dV (plus a mis-scaled dQ) at real activation magnitudes. Forward was exact and unit-scale tests passed, which is how it survived — the Triton path is only load-bearing off-Hopper (sm_90 uses the ThunderKittens CUDA backward). Fix: pass raw K, apply sm_scale*RCP_LN2 after tl.dot in fp32 in both _attn_bwd_dkdv and _attn_bwd_dq, and scale dq by sm_scale instead of LN2. Verified against SDPA to 4 significant digits at sm_scale 1/8/32 and at the real H3 geometry (37,48,84 tiles, 128-dim heads). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-08-11 04:40:58 +00:00
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
3 people	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
xsankandmergify[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
4 people	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
RoyWangandroywang	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 LinandShreejithSG	2f6230abcf	[kernel] Reorg and fix fastvideo-kernel (#962) ... Co-authored-by: ShreejithSG <shreejithsg@gmail.com>	2025-12-26 01:50:24 -06:00