xuebwang-amd 44eea10f68 [ROCm][Quantization] make quark ocp mx dtype parser robust for weight-only quantization (#36232) ...

Signed-off-by: xuebwang-amd <xuebwang@amd.com>

2026-03-20 10:10:03 -05:00

..

schemes

[ROCm][Quantization] make quark ocp mx dtype parser robust for weight-only quantization (#36232)

2026-03-20 10:10:03 -05:00

__init__.py

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

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

quark_moe.py

[ROCm][Quantization] make quark ocp mx dtype parser robust for weight-only quantization (#36232)

2026-03-20 10:10:03 -05:00

quark.py

Fix infinite recursive search issue in quark.py (#32779)

2026-03-17 07:19:15 +00:00

utils.py

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

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