cturan/llama.cpp

镜像自地址 https://github.com/cturan/llama.cpp

作者	SHA1 备注	提交日期
Georgi Gerganov	f0d3c7405c batched-bench : use rand tokens (#15398)	5 月之前
Georgi Gerganov	225e7a1438 llama : add high-throughput mode (#14363)	6 月之前
Georgi Gerganov	745aa5319b llama : deprecate llama_kv_self_ API (#14030)	7 月之前
Georgi Gerganov	b89d605a91 batched-bench : fix pp batch contents (#13492)	8 月之前
Diego Devesa	1d36b3670b llama : move end-user examples to tools directory (#13249)	8 月之前