1
3 commits
1 linked in READMEs
updated May 4, 2024
2 commits
1 commits
mit-han-lab/Yi-34B-QServe-g128
mit-han-lab/Llama-3-8B-QServe
relaxml/Llama-2-7b-E8PRVQ-3Bit
0
relaxml/Llama-2-7b-E8PRVQ-4Bit
relaxml/Llama-2-70b-E8PRVQ-3Bit
mit-han-lab/Llama-3-8B-QServe-g128
relaxml/Llama-2-13b-E8PRVQ-3Bit
relaxml/Llama-2-13b-E8PRVQ-4Bit
mit-han-lab/omniserve
[MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25]…
860
