mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-27 22:23:25 +08:00
Support DeepSeek-R1 W4A8 on Hopper Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com> Co-authored-by: Jiang Shao <91270701+StudyingShao@users.noreply.github.com> Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| _utils.py | ||
| test_fp8_quantization.py | ||
| test_fp8_rowwise_gemm.py | ||
| test_functional.py | ||
| test_mode.py | ||
| test_moe_weight_only_groupwise_quant_matmul.py | ||
| test_qserve_gemm.py | ||
| test_quant_layer.py | ||
| test_quant.py | ||
| test_smooth_quant_gemm.py | ||
| test_smooth_quant_layer_norm.py | ||
| test_smooth_quant_rms_norm.py | ||
| test_weight_only_groupwise_quant_matmul.py | ||
| test_weight_only_quant_matmul.py | ||