meng-amd 6df2b1a8c6 [Quantization] Support native Quark W4A16 INT4/UINT4 exports in vLLM (#48606) ...

Signed-off-by: HongWei Meng <HongWei.Meng@amd.com>

2026-09-18 17:52:46 +08:00

..

__init__.py

[Quantization] Support native Quark W4A16 INT4/UINT4 exports in vLLM (#48606)

2026-09-18 17:52:46 +08:00

quark_nvfp4.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

quark_ocp_mx.py

[Quantization][Refactor][1/N] Adopt QuantKey in QuarkConfig and methods, relying on weight_quant_key, act_quant_key for quant method dispatch (#52958)

2026-09-01 02:55:54 -05:00

quark_scheme.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

quark_w4a8_mxfp4_fp8.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

quark_w4a16_int4.py

[Quantization] Support native Quark W4A16 INT4/UINT4 exports in vLLM (#48606)

2026-09-18 17:52:46 +08:00

quark_w8a8_fp8.py

[ROCm] Expose kFp8DynamicTokenSym on AITER PTPC linears (#54248)

2026-09-16 11:48:30 -05:00

quark_w8a8_int8.py

[Quantization][Refactor][1/N] Adopt QuantKey in QuarkConfig and methods, relying on weight_quant_key, act_quant_key for quant method dispatch (#52958)

2026-09-01 02:55:54 -05:00