Dipika Sikka d272415e57 [Quantization] Expand compressed-tensors MoE matching logic to support NFP4 + FP8 MoEs (#22674) ...

Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>

2025-08-27 05:00:21 +00:00

..

schemes

[quantization] use channel scales for w4a8 + misc fixes (#23570)

2025-08-26 18:23:23 -07:00

__init__.py

[Kernel] Initial Activation Quantization Support (#4525)

2024-05-23 21:29:18 +00:00

compressed_tensors_moe.py

[Quantization] Expand compressed-tensors MoE matching logic to support NFP4 + FP8 MoEs (#22674)

2025-08-27 05:00:21 +00:00

compressed_tensors.py

[Quantization] Expand compressed-tensors MoE matching logic to support NFP4 + FP8 MoEs (#22674)

2025-08-27 05:00:21 +00:00

triton_scaled_mm.py

[AMD][Kernel][BugFix] fix test_rocm_compressed_tensors_w8a8 for rocm (#19509)

2025-06-12 07:14:24 +00:00

utils.py

[Quantization] Add compressed-tensors NVFP4 support (#18312)

2025-06-08 09:05:55 -04:00