Bowen Bao 1e9500410a [ROCm][Quantization][2/N] Refactor quark_moe w4a8 w/ oracle (#39136) ...

Signed-off-by: Bowen Bao <bowenbao@amd.com>

2026-05-04 19:50:38 -07:00

..

schemes

[Bugfix][ROCm] Fix gemm_a4w4 call to use updated AITER API signature (#40754)

2026-04-29 09:04:53 +09:00

__init__.py

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

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

quark_moe.py

[ROCm][Quantization][2/N] Refactor quark_moe w4a8 w/ oracle (#39136)

2026-05-04 19:50:38 -07:00

quark.py

[ROCm] Add env flags to disable dynamic MXFP4 quant and enable AITER tuned GEMMs for Attention Projection Layers (#39987)

2026-04-29 16:07:46 -07:00

utils.py

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

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