AlpinDale ba371fbbbd feat: AWQ marlin kernels (#603) | vor 5 Monaten | |
---|---|---|
.. | ||
amd | 251568470e initial nvidia fp8 e4m3 for kv cache | vor 6 Monaten |
nvidia | 3bdeb3e116 fix: clang formatting for all kernels (#558) | vor 6 Monaten |
common.cu | c8f5424d72 add scale_ub inputs to fp8 dynamic per-token quant | vor 5 Monaten |
fp8_marlin.cu | ba371fbbbd feat: AWQ marlin kernels (#603) | vor 5 Monaten |