微软BitDistill将LLM压缩到1.58比特：10倍内存节省、2.65倍CPU推理加速
"Quantization" 相关文章
微软BitDistill将LLM压缩到1.58比特：10倍内存节省、2.65倍CPU推理加速
QeRL: NVFP4-Quantized Reinforcement Learning (RL) Brings 32B LLM Training to a Single H100—While Improving Exploration
Unlock Faster, Smarter Edge Models with 7x Gen AI Performance on NVIDIA Jetson AGX Thor
Unlock Faster, Smarter Edge Models with 7x Gen AI Performance on NVIDIA Jetson AGX Thor
Huawei's new open source technique shrinks LLMs to make them run on less powerful, less expensive hardware
Huawei's new open source technique shrinks LLMs to make them run on less powerful, less expensive hardware
Deploy FLAN-T5 XXL on Amazon SageMaker
Accelerate Mixtral 8x7B with Speculative Decoding and Quantization on Amazon SageMaker
Top 10 Local LLMs (2025): Context Windows, VRAM Targets, and Licenses Compared
8GB显存笔记本能跑多大AI模型？这个计算公式90%的人都不知道！
I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation
让机器人“大脑”更轻更快：SQAP-VLA首次实现VLA模型量化与剪枝协同加速
Double PyTorch Inference Speed for Diffusion Models Using Torch-TensorRT
Double PyTorch Inference Speed for Diffusion Models Using Torch-TensorRT
