註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Andrei Panferov @ICLR
@black_samorez
ML PhD Candidate @ISTAustria and @EllisForEurope
加入 September 2020
185 正在關注    212 粉絲
Disaggregated quantization for LLMs 🧵 LLM prefill and decode can be processed by separate weights in different precisions. Boosts speed AND accuracy. Offloading makes it zero-overhead on long sequences for dense models. Applicable to existing quantized checkpoints. Paper: Code: Qwen3.8 NVFP4 prefillers:
顯示更多
0
5
50
17
轉發到社區