Canlin Guo 4f6885fffc [DSV4][Kernel] Fuse shared experts into MegaMoE (#53040) ...

Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>

2026-08-20 12:07:02 -07:00

..

amd

Reduce AutoWeightsLoader kwargs (#53106)

2026-08-20 15:40:11 +00:00

common

[ROCm] Fix DeepSeek V4 indexer numerics and coverage (#50803)

2026-08-20 09:34:00 +00:00

nvidia

[DSV4][Kernel] Fuse shared experts into MegaMoE (#53040)

2026-08-20 12:07:02 -07:00

xpu

Reduce AutoWeightsLoader kwargs (#53106)

2026-08-20 15:40:11 +00:00

__init__.py

[XPU] Add DSpark speculative decoding support for DeepSeek-V4 (#47677)

2026-07-15 17:59:02 -07:00

attention.py

Revert DSv4 eager workspace reuse (#52836)

2026-08-18 17:02:59 -07:00

compressor.py

Revert DSv4 eager workspace reuse (#52836)

2026-08-18 17:02:59 -07:00

quant_config.py

[Quantization] Remove dead QuantizationConfig.is_mxfp4_quant (#51793)

2026-08-13 13:58:31 -04:00

sparse_mla.py

[Bugfix][DSv4] Revert adaptive C128A metadata packing (#51318)

2026-08-15 18:39:23 -07:00