3 people c5bda658d2 [Model][MoE] Load MegaMoE experts directly into the DeepGEMM layout (#60096) ...

Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: Aaron Hao <hao-aaron@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Aaron Hao <hao-aaron@users.noreply.github.com>

2026-10-13 11:52:08 -07:00

..

amd

[ROCm][DSv4] Fuse the shared expert into AITER MegaMoE (#61004)

2026-10-12 15:53:16 +08:00

common

[Kernel][Build] Bump DeepGEMM to the 26/09/30 release and adapt the sparse indexer (#61149)

2026-10-12 23:24:43 -07:00

cpu

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

nvidia

[Model][MoE] Load MegaMoE experts directly into the DeepGEMM layout (#60096)

2026-10-13 11:52:08 -07:00

xpu

[Bugfix][XPU] Make DeepSeek V4 FP8 sparse decode graph-capturable (#59159)

2026-10-04 18:31:15 +08:00

__init__.py

[Model][ROCm] Enable DeepSeek V4 Vision (#55107)

2026-09-11 09:17:30 -07:00

attention.py

[KV-Offloading][TP] : Expand replicated_layout detection to multi-group MLA (#57652)

2026-09-30 09:11:03 -04:00

compressor.py

[Bugfix][DSv4] Don't bake the C128 compressor skip into CUDA graphs (#59709)

2026-10-13 10:15:11 +00:00

quant_config.py

[quantization] Add per-token NVFP4 quantization MoE support for ReLU2 (#56740)

2026-10-07 22:01:09 +00:00

sparse_mla.py

[Kernel] Resubmit PR 48666 - Gemma4 FP8 KV FA4 head dim 512 backend selection (#53175)

2026-09-23 20:29:06 -07:00

vl_stub.py

[Model][ROCm] Enable DeepSeek V4 Vision (#55107)

2026-09-11 09:17:30 -07:00