marcsun13's picture
marcsun13 HF Staff
GGUF kernels: dequantize + fused gemv over packed blocks, 9 CUDA variants
2c20074 verified
Raw
History Blame Contribute Delete
1.6 kB
[
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype0-Q4_K]",
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype0-Q5_K]",
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype0-Q6_K]",
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype0-Q8_0]",
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype1-Q4_K]",
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype1-Q5_K]",
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype1-Q6_K]",
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype1-Q8_0]",
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype2-Q4_K]",
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype2-Q5_K]",
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype2-Q6_K]",
"tests/test_gguf_kernels.py::test_dequantize_matches_reference[dtype2-Q8_0]",
"tests/test_gguf_kernels.py::test_gemv_is_compileable",
"tests/test_gguf_kernels.py::test_mul_mat_vec_matches_matmul[1-Q4_K]",
"tests/test_gguf_kernels.py::test_mul_mat_vec_matches_matmul[1-Q5_K]",
"tests/test_gguf_kernels.py::test_mul_mat_vec_matches_matmul[1-Q6_K]",
"tests/test_gguf_kernels.py::test_mul_mat_vec_matches_matmul[1-Q8_0]",
"tests/test_gguf_kernels.py::test_mul_mat_vec_matches_matmul[8-Q4_K]",
"tests/test_gguf_kernels.py::test_mul_mat_vec_matches_matmul[8-Q5_K]",
"tests/test_gguf_kernels.py::test_mul_mat_vec_matches_matmul[8-Q6_K]",
"tests/test_gguf_kernels.py::test_mul_mat_vec_matches_matmul[8-Q8_0]"
]