Divakar Verma 6341d43043 [ROCm][Quantization] add quark w4a8 mxfp4_fp8 for LinearLayer (#35316) ...

Signed-off-by: Divakar Verma <divakar.verma@amd.com>

2026-03-13 19:44:24 +00:00

..

schemes

[ROCm][Quantization] add quark w4a8 mxfp4_fp8 for LinearLayer (#35316)

2026-03-13 19:44:24 +00:00

__init__.py

[Misc][Quark] Upstream Quark format to VLLM (#10765)

2025-01-15 11:05:15 -05:00

quark_moe.py

[Hardware] Replace torch.cuda.empty_cache with torch.accelerator.empty_cache (#30681)

2026-03-04 09:49:47 +00:00

quark.py

[ROCm][Quantization] add quark w4a8 mxfp4_fp8 for LinearLayer (#35316)

2026-03-13 19:44:24 +00:00

utils.py

[ROCM] DSfp4 mla projection gemms weight dynamic quantization (#32238)

2026-01-15 14:13:08 -06:00