註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

filipe
@filicroval
data eng | serendipity business inquiries: filipe@filicroval.com
加入 May 2023
297 正在關注    153.5K 粉絲
legendary drop from NVIDIA: ModelOpt 0.45.0 biggest additions: - New NVFP4 (W4A16) weight-only quantization format that requires no calibration - Better MoE support (including mixed NVFP4 + FP8 recipes for models like Nemotron) - Easy MXFP4 → NVFP4 conversion for models like DeepSeek V4 and GPT-OSS - Various improvements for large-scale PTQ and Megatron workflows looks like NVIDIA is pushing harder on making 4-bit inference more practical and calibration-free.
顯示更多