68 Commits (eebe4cb1200fa858bafe72e204eb8abffc05f4c0)

Author SHA1 Message Date
  Martin Evans 4d72420a04 Replaced `SaveState` and `LoadState` implementations. These new implementations map the file into memory and then pass the pointer directly into the native API. This improves things in two ways: 2 years ago
  SignalRT 56a37a0d7d Update to lates llama.cpp 2 years ago
  unknown dba866ffcf Update API method name 2 years ago
  Yaohui Liu 1062fe1a7e
feat: upgrade the native libraries. 2 years ago
  Yaohui Liu 9850417a12
feat: update quantize native params. 2 years ago
  Yaohui Liu 3bf74ec9b9
feat: add chat session for refactored code. 2 years ago
  Yaohui Liu 264fb9a706
refactor: LLamaModel and LLamaExecutor. 2 years ago
  Yaohui Liu 3a62f087fe
fix: encoding error when using other languages. 2 years ago
  Yaohui Liu 18c2ff2395
refactor: instruct mode and examples. 2 years ago
  Yaohui Liu 55d5a8ae51
fix: quantization error with fp16. 2 years ago
  Yaohui Liu 19979f664a
feat: support loading and saving state. 2 years ago
  Yaohui Liu 4314f64b9c
feat: add check for backend package. 2 years ago
  Yaohui Liu 6ffcb5306b
refactor: use official api of quantization instead. 2 years ago
  Yaohui Liu 118d410d52
build: revise build informations. 2 years ago
  Yaohui Liu 856d6549de build: add linux support. 2 years ago
  Yaohui Liu 02524ae4eb
build: add package informations. 2 years ago
  Yaohui Liu d6a7997e46
feat: add gpt model. 2 years ago
  Yaohui Liu 5a79edeb51
feat: add the framework and basic usages. 2 years ago