You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
Martin Evans 3b0b2ab224
Merge pull request #721 from martindevans/kv_cache_view
2 years ago
..
DecodeResult.cs Swapped `StatelessExecutor` to use `llama_decode`! 2 years ago
GGMLType.cs Added a comment on the type itself 2 years ago
GPUSplitMode.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 2 years ago
GroupDisposable.cs - Added `GroupDisposable` to dispose a collection of items all together 2 years ago
LLamaBatch.cs Fixed off by one error in LLamaBatch sampling position (#626) 2 years ago
LLamaBeamView.cs April 2024 Binary Update (#662) 2 years ago
LLamaBeamsState.cs April 2024 Binary Update (#662) 2 years ago
LLamaChatMessage.cs - Added `LLamaTemplate` which efficiently formats a series of messages according to the model template. 2 years ago
LLamaContextParams.cs - Added `LLamaWeights.LoadFromFileAsync`. 2 years ago
LLamaFtype.cs April 2024 Binary Update (#662) 2 years ago
LLamaGrammarElement.cs Improved test coverage. Discovered some issues: 2 years ago
LLamaKvCacheView.cs Expanded the `LLamaKvCacheView` to make it usable without unsafe. 2 years ago
LLamaLogLevel.cs Logging interceptor (#649) 2 years ago
LLamaModelMetadataOverride.cs March Binary Update (#565) 2 years ago
LLamaModelParams.cs - Added `LLamaWeights.LoadFromFileAsync`. 2 years ago
LLamaModelQuantizeParams.cs April 2024 Binary Update (#662) 2 years ago
LLamaNativeBatch.cs Removed `LLamaBatchSafeHandle` (using unmanaged memory, created by llama.cpp) and replaced it with a fully managed `LLamaBatch`. Modified the `BatchedDecoding` example to use new managed batch. 2 years ago
LLamaPoolingType.cs April 2024 Binary Update (#662) 2 years ago
LLamaPos.cs Added increment and decrement operators to `LLamaPos` 2 years ago
LLamaRopeType.cs March Binary Update (#565) 2 years ago
LLamaSeqId.cs Removed `LLamaBatchSafeHandle` (using unmanaged memory, created by llama.cpp) and replaced it with a fully managed `LLamaBatch`. Modified the `BatchedDecoding` example to use new managed batch. 2 years ago
LLamaToken.cs Added a test with examples of troublesome strings from 0.9.1 2 years ago
LLamaTokenData.cs made casts to/from int explicit, fixed places affected 2 years ago
LLamaTokenDataArray.cs Classifier Free Guidance (#536) 2 years ago
LLamaTokenType.cs Assorted small changes to clean up some code warnings 2 years ago
LLamaVocabType.cs April 2024 Binary Update (#662) 2 years ago
LLavaImageEmbed.cs Llava api (#563) 2 years ago
NativeApi.BeamSearch.cs Code cleanup driven by R# suggestions: 2 years ago
NativeApi.Grammar.cs - Removed unnecessary constructors from safe handles 2 years ago
NativeApi.LLava.cs fix: typos. 2 years ago
NativeApi.Load.cs fix: typos. 2 years ago
NativeApi.Quantize.cs Modified `llama_model_quantize` to accept argument by `ref` instead of pointer. 2 years ago
NativeApi.Sampling.cs Classifier Free Guidance (#536) 2 years ago
NativeApi.cs Merge pull request #721 from martindevans/kv_cache_view 2 years ago
NativeLibraryConfig.cs fix: typos. 2 years ago
NativeLogConfig.cs Logging interceptor (#649) 2 years ago
RopeScalingType.cs March Binary Update (#565) 2 years ago
SafeLLamaContextHandle.cs Add method to get BOS token. 2 years ago
SafeLLamaGrammarHandle.cs Using `is` check instead of `== null` 2 years ago
SafeLLamaHandleBase.cs - Removed one of the constructors of `SafeLLamaHandleBase`, which implicitly states that memory is owned. Better to be explicit about this kind of thing! 2 years ago
SafeLlamaModelHandle.cs - Added `LLamaWeights.LoadFromFileAsync`. 2 years ago
SafeLlavaImageEmbedHandle.cs - Removed unnecessary constructors from safe handles 2 years ago
SafeLlavaModelHandle.cs - Added `LoadFromFileAsync` method for `LLavaWeights` 2 years ago