EdalatiAli e5b807607c [Quant][Feature] Support online MXFP8 quantization for MoE and dense models (#35448) ...

Signed-off-by: EdalatiAli <aliedalati@cohere.com>

2026-03-16 18:07:39 -04:00

..

fixtures

…

language

[Model] Add HyperCLOVAX-SEED-Think-14B language model support (#37107)

2026-03-16 06:40:05 +00:00

multimodal

[Bugfix] Make siglip/clip compatible with transformers v5 (#37200)

2026-03-16 16:48:18 +00:00

quantization

[Quant][Feature] Support online MXFP8 quantization for MoE and dense models (#35448)

2026-03-16 18:07:39 -04:00

__init__.py

…

registry.py

[Model] Add HyperCLOVAX-SEED-Think-14B language model support (#37107)

2026-03-16 06:40:05 +00:00

test_gguf_download.py

…

test_initialization.py

…

test_oot_registration.py

…

test_registry.py

…

test_terratorch.py

…

test_transformers.py

…

test_utils.py

…

test_vision.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

utils.py

[CI] Revert PRs 34818 and 33600 (#34979)

2026-02-20 13:25:50 -08:00