Yufeng He 4673ca1d78 fix: prefix DeepSeek V4 MTP projections (#44821) ...

Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com>

2026-06-10 08:47:04 -07:00

..

amd

fix: prefix DeepSeek V4 MTP projections (#44821)

2026-06-10 08:47:04 -07:00

common

[DSv4] Adding TRTLLM gen attention kernel (#43827)

2026-06-04 07:35:09 -07:00

nvidia

fix: prefix DeepSeek V4 MTP projections (#44821)

2026-06-10 08:47:04 -07:00

xpu

[DSV4][XPU] Add MHC fused_post_pre support (#44144)

2026-06-09 17:23:17 +08:00

__init__.py

[XPU]feat: add DeepSeek-V4 XPU attention decode path (#42953)

2026-06-08 13:27:12 +08:00

attention.py

[DSV4] Move more ops out of eager breakpoint (#44561)

2026-06-05 06:42:41 -07:00

compressor.py

[XPU]feat: add DeepSeek-V4 XPU attention decode path (#42953)

2026-06-08 13:27:12 +08:00

quant_config.py

[Bugfix] Fix weight loading issues caused by #41184 (#45054)

2026-06-10 01:20:13 -04:00

sparse_mla.py

[DSV4] Decouple DS V4 Sparse MLA Metadata from DS V3.2 (#44699)

2026-06-06 20:37:56 -04:00