85 Commits (4d7d4f2bfef46028662720d022a2ba4ed09fc921)

Author SHA1 Message Date
  Rinne 4d7d4f2bfe
Merge pull request #59 from saddam213/master 3 years ago
  Rinne 66d6b00b49
Merge pull request #57 from martindevans/larger_states 3 years ago
  Rinne c5e8b3eba2
Merge pull request #56 from martindevans/memory_mapped_save_loading_and_saving 3 years ago
  Rinne dee9afc471
Merge pull request #55 from martindevans/removed_dictionary_extensions 3 years ago
  Rinne d17fa991cc
Merge pull request #53 from martindevans/xml_docs_fixes 3 years ago
  sa_ddam213 3fec7a63c7 Add Instruct and Stateless support 3 years ago
  Rinne 36ad09790c
Merge branch 'master' into master 3 years ago
  Rinne 1b0523f630
Merge branch 'master' into master 3 years ago
  SignalRT e5d885050e Align llama.cpp binaries 3 years ago
  Martin Evans f3fa73de2b Implemented a new `LlamaModel.State` handle which internally stores the state as natively allocated memory. This allows it to exceed the 2GB limit on C# arrays. 3 years ago
  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: 3 years ago
  Martin Evans 18462beb31 - Removed the `Update` and `GetOrDefault` extension methods (they were unused). 3 years ago
  Martin Evans 2e76b79af6 Various minor XML docs fixes 3 years ago
  Faisal Waris 17838bba49 fix breaking change in llama.cpp; bind to latest version llama.cpp to support new quantization method 3 years ago
  SignalRT a5c089e7b1 Update llama.cpp libraries 3 years ago
  SignalRT 56a37a0d7d Update to lates llama.cpp 3 years ago
  unknown dba866ffcf Update API method name 3 years ago
  SignalRT b1019ae46f Update the latest llama.cpp metal libraries 3 years ago
  SignalRT fb9e38d3e8 Update llama.cpp 3 years ago
  SignalRT 37975f405f Libraries with MacOS Metal Support 3 years ago
  SignalRT 2fde2020a5 Update libllama.dylib 3 years ago
  Rinne 0269af8c17
Merge branch 'master' into runtime-targets 3 years ago
  Yaohui Liu 1062fe1a7e
feat: upgrade the native libraries. 3 years ago
  Yaohui Liu 9850417a12
feat: update quantize native params. 3 years ago
  Yaohui Liu 6c400e64c2
docs: publiash documentation 0.4. 3 years ago
  Yaohui Liu 2eb2d6df83
test: add 9 examples of the new version. 3 years ago
  Tim Miller 49f664646e Remove packaging targets file 3 years ago
  Tim Miller bbd2650cf0 Include runtime targets file 3 years ago
  Yaohui Liu f3565d6b2d
refactor: rename Quantizer to LLamaQuantizer. 3 years ago
  Yaohui Liu b20b6f209e
docs: add some xml comments. 3 years ago
  Yaohui Liu 1e061615d4
refactor: remove SessionParams. 3 years ago
  Rinne 08e668a313
Merge pull request #26 from mlof/document-interfaces 3 years ago
  Marcel 65925eac4f Added documentation for the interfaces 3 years ago
  Marcel b911b2548b move interfaces into abstractions folder 3 years ago
  Marcel 762fd7c1ae Fixed a typo in FixedSizeQueue 3 years ago
  Rinne 69849d3fc0
Merge pull request #24 from SignalRT/master 3 years ago
  Yaohui Liu a3b8186f20
feat: support save and load chat session. 3 years ago
  Yaohui Liu bdbd6aa824
feat: add transforms for chat session. 3 years ago
  SignalRT 429af3d234
Merge branch 'SciSharp:master' into master 3 years ago
  Yaohui Liu b567399b65
refactor: allow customized logger. 3 years ago
  SignalRT b326dfc43f MacOS Support 3 years ago
  SignalRT f7cf453366 MacOS Dynamic Link Libraries 3 years ago
  Yaohui Liu 3bf74ec9b9
feat: add chat session for refactored code. 3 years ago
  Yaohui Liu 908b79e855
feat: add stateless executor. 3 years ago
  Yaohui Liu e603a09137
fix: state loading and saving not working. 3 years ago
  Yaohui Liu 5679e08718
feat: add ILLamaExecutor.InferAsync. 3 years ago
  Yaohui Liu 264fb9a706
refactor: LLamaModel and LLamaExecutor. 3 years ago
  Yaohui Liu 3a62f087fe
fix: encoding error when using other languages. 3 years ago
  Yaohui Liu 9a4bf8e844
docs: add verified models info. 3 years ago
  Yaohui Liu e77afa76d0
feat: change default param of n_gpu_layers to 20. 3 years ago