RuQing Xu ab459b36c2 [Kernel] Refresh FlashInfer attention; Add quantized attention support (Blackwell QK16/V8) (#5344) ...

Signed-off-by: Ruqing Xu <7891482+xrq-phys@users.noreply.github.com>

2026-08-07 16:14:26 +08:00

..

diffusion

[Kernel] Refresh FlashInfer attention; Add quantized attention support (Blackwell QK16/V8) (#5344)

2026-08-07 16:14:26 +08:00

examples

[docs] consolidate diffusion execution modes (#5599)

2026-08-05 22:41:18 +08:00

quantization

docs: document distributed layerwise offload compatibility (#5839)

2026-08-06 23:21:43 +08:00

diffusion_features.md

docs: document distributed layerwise offload compatibility (#5839)

2026-08-06 23:21:43 +08:00

fault_injection_reliability_matrix.md

[Refactor] Remove legacy --stage-configs-path from the serve CLI (#5647)

2026-08-03 23:41:52 +08:00

feature_compatibility.md

[skip ci][Doc] Refine the Diffusion Features User Guide (#1928)

2026-03-30 14:28:04 +08:00