AlpinDale ad24e74a99 feat: FP8 weight-only quantization support for Ampere GPUs преди 6 месеца
..
amd 251568470e initial nvidia fp8 e4m3 for kv cache преди 7 месеца
nvidia 3bdeb3e116 fix: clang formatting for all kernels (#558) преди 7 месеца
common.cu 37c6da9eb3 feat: vectorized fp8 quant kernel преди 7 месеца
fp8_marlin.cu ad24e74a99 feat: FP8 weight-only quantization support for Ampere GPUs преди 6 месеца