ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟andGitHub a31614e386 [ROCm][Quantization][Kernel] Use FP8 FNUZ when OCP flag is 0 or undefined (#13851) ...

Signed-off-by: Hollow Man <hollowman@opensuse.org>

2025-02-27 10:39:10 +08:00

..

amd

[ROCm][Quantization][Kernel] Use FP8 FNUZ when OCP flag is 0 or undefined (#13851)

2025-02-27 10:39:10 +08:00

nvidia

[CI/Build] Suppress divide-by-zero and missing return statement warnings (#7001)

2024-08-05 16:00:01 -04:00

common.cu

[torch.compile] Fuse RMSNorm with quant (#9138)

2024-11-08 21:20:08 +00:00

common.cuh

[ROCm][Quantization][Kernel] Using HIP FP8 header (#12593)

2025-02-25 00:39:59 -08:00

fp8_marlin.cu

[CI/Build] Per file CUDA Archs (improve wheel size and dev build times) (#8845)

2024-10-03 22:55:25 -04:00