aoshen02andaoshen02 69cf055936 [Performance][DSv4] Size dequant gather launch grid by rows (#55061) ...

Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen524@gmail.com>

2026-09-03 20:06:34 -07:00

..

amd

[ROCm][Perf] Fuse SWA q/kv RMSNorm and q FP8 group quant for DeepSeek-V4 (#53540)

2026-08-27 09:37:54 -07:00

common

[New model][Multimodal] Add DeepSeek-V4-Flash-Vision-Exp support (#54566)

2026-09-02 11:09:09 -07:00

nvidia

[Performance][DSv4] Size dequant gather launch grid by rows (#55061)

2026-09-03 20:06:34 -07:00

xpu

Reduce AutoWeightsLoader kwargs (#53106)

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

__init__.py

[New model][Multimodal] Add DeepSeek-V4-Flash-Vision-Exp support (#54566)

2026-09-02 11:09:09 -07:00

attention.py

Fix DeepSeek V4 FlashMLA auto KV cache dtype (#45091)

2026-09-03 19:29:14 +00:00

compressor.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -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][SM120] DSv4: pass contiguous C128A decode topk indices on SM120 (#53574)

2026-08-31 09:44:42 +00:00

vl_stub.py

[New model][Multimodal] Add DeepSeek-V4-Flash-Vision-Exp support (#54566)

2026-09-02 11:09:09 -07:00