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 15a98b36d8 Updated everything to work with llama.cpp ce32060198 1 year ago
..
DecodeResult.cs Swapped `StatelessExecutor` to use `llama_decode`! 1 year ago
GGMLType.cs Added a comment on the type itself 1 year ago
GPUSplitMode.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
GroupDisposable.cs - Added `GroupDisposable` to dispose a collection of items all together 1 year ago
LLamaBatch.cs Added methods to `SafeLLamaContextHandle` for KV cache manipulation 1 year ago
LLamaBeamView.cs Switched form using raw integers, to a `LLamaToken` struct 1 year ago
LLamaBeamsState.cs Debugging slowdown by removing some things: 2 years ago
LLamaContextParams.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
LLamaFtype.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
LLamaGrammarElement.cs Improved test coverage. Discovered some issues: 2 years ago
LLamaKvCacheView.cs Added methods to `SafeLLamaContextHandle` for KV cache manipulation 1 year ago
LLamaLogLevel.cs Extract LLamaLogLevel, Remove Logger class 2 years ago
LLamaModelMetadataOverride.cs Fixed alignment of value fields in `LLamaModelMetadataOverride` 1 year ago
LLamaModelParams.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
LLamaModelQuantizeParams.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year 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. 1 year ago
LLamaPos.cs Code cleanup driven by R# suggestions: 1 year 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. 1 year ago
LLamaToken.cs Added a test with examples of troublesome strings from 0.9.1 1 year ago
LLamaTokenData.cs made casts to/from int explicit, fixed places affected 1 year ago
LLamaTokenDataArray.cs made casts to/from int explicit, fixed places affected 1 year ago
LLamaTokenType.cs Code cleanup driven by R# suggestions: 1 year ago
NativeApi.BeamSearch.cs Code cleanup driven by R# suggestions: 1 year ago
NativeApi.Grammar.cs Switched form using raw integers, to a `LLamaToken` struct 1 year ago
NativeApi.Load.cs Fix missing library name prefix for cuda 1 year ago
NativeApi.Quantize.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
NativeApi.Sampling.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
NativeApi.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
NativeLibraryConfig.cs Code cleanup driven by R# suggestions: 1 year ago
RopeScalingType.cs Exposed YaRN scaling parameters in IContextParams 2 years ago
SafeLLamaContextHandle.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
SafeLLamaGrammarHandle.cs - Removed one of the constructors of `SafeLLamaHandleBase`, which implicitly states that memory is owned. Better to be explicit about this kind of thing! 1 year 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! 1 year ago
SafeLlamaModelHandle.cs Merge pull request #438 from martindevans/cleanup_model_unnecessary_unsafe 1 year ago
SamplingApi.cs Switched form using raw integers, to a `LLamaToken` struct 1 year ago