Xiangyu LiandGitHub 5cc6bddb6e [Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by adapting gptq_gemm (#26092)

2025-10-23 23:26:13 -04:00

..

attention

…

core

…

mamba

…

moe

…

quantization

[Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by adapting gptq_gemm (#26092)

2025-10-23 23:26:13 -04:00

__init__.py

…

allclose_default.py

…

quant_utils.py

…

test_apply_repetition_penalties.py

…

test_fla_layernorm_guard.py

…

test_flex_attention.py

…

test_fused_quant_activation.py

…

test_onednn.py

…

test_shuffle_rows.py

…

test_top_k_per_row.py

…

test_triton_flash_attention.py

…

utils.py

…