Xinyu Kang 6671cfc775 [AMD] Fix weight checking for AITER-shuffled block FP8 weights (#34330)

2026-09-11 15:49:56 -07:00

..

attention

[Diffusion][MiniMax-H3] Add SM90 Sage compute for SubBlock sparse attention (#37982)

2026-09-09 20:00:03 +08:00

diffusion

[Diffusion] Optimize SANA-WM convolution post-processing and streaming GDN (#38529)

2026-09-11 23:30:17 +08:00

embeddings

support qwen 3.8 flash next (#37500)

2026-09-08 13:56:21 -07:00

hyperconnection

support qwen 3.8 flash next (#37500)

2026-09-08 13:56:21 -07:00

jit

support qwen 3.8 flash next (#37500)

2026-09-08 13:56:21 -07:00

ops/attention

Store mamba prefix-cache checkpoints at the configured SSM state dtype (#34820)

2026-09-09 15:25:57 +08:00

qsa

fix(qsa): make the paged sparse-decode gather memory-safe (zero-fill scratch, int64 offsets, dequant FP8 on gather) (#38851)

2026-09-11 15:47:25 -07:00

quantization

[AMD] Fix weight checking for AITER-shuffled block FP8 weights (#34330)

2026-09-11 15:49:56 -07:00

speculative

[AMD] Parallelize aiter spec-decode KV index building over token blocks (#37659)

2026-09-09 17:53:53 -07:00