Shiwen Tang 0711c1abfa [Feature] Support AWQ MoE W4A16 Quantization (#142) ...

Signed-off-by: tangshiwen <tangshiwen@baidu.com>
Co-authored-by: Li Wei <liwei.109@outlook.com>

2026-01-26 18:56:05 +08:00

..

compressed_tensors

add 2 kernels and optimize the calculation of topk_indices (#134)

2026-01-22 10:29:28 +08:00

kernels

[Feature] Support AWQ MoE W4A16 Quantization (#142)

2026-01-26 18:56:05 +08:00

__init__.py

Initial commit for vLLM-Kunlun Plugin

2025-12-10 12:05:39 +08:00

awq.py

[Feature] Support AWQ MoE W4A16 Quantization (#142)

2026-01-26 18:56:05 +08:00

gptq.py

[refactor]update Kunlun classes with monkey patch (#122)

2026-01-19 20:24:19 +08:00

moe_wna16.py

[Feature] Support AWQ MoE W4A16 Quantization (#142)

2026-01-26 18:56:05 +08:00