Matej SirovatkaandJee Jee Li 3ac9525507 [Bugfix][Quantization] Reuse online NVFP4 MoE kernel across reloads (#50074) ...

Signed-off-by: S1ro1 <matej.sirovatka@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>

2026-08-12 14:06:53 +08:00

..

__init__.py

[Frontend] new online quantization frontend (#38138)

2026-04-03 11:58:39 -04:00

base.py

[Online quantization] Add online MXFP4 quantization support (#49347)

2026-08-07 12:39:46 -07:00

fp8.py

[Online quantization] Add online MXFP4 quantization support (#49347)

2026-08-07 12:39:46 -07:00

int8.py

[Refactor] refactor humming linear and moe backends to use explicit layer configs (#49610)

2026-08-07 10:03:19 -07:00

moe_base.py

[Online quantization] Add online MXFP4 quantization support (#49347)

2026-08-07 12:39:46 -07:00

mxfp4.py

[Bugfix] Drop stale layer kwarg from online MXFP4 kernel creation (fix precommit) (#51442)

2026-08-07 13:49:00 -07:00

mxfp8.py

[Refactor] refactor humming linear and moe backends to use explicit layer configs (#49610)

2026-08-07 10:03:19 -07:00

nvfp4.py

[Bugfix][Quantization] Reuse online NVFP4 MoE kernel across reloads (#50074)

2026-08-12 14:06:53 +08:00