LLamaSharp/LLama/Native
jlsantiago 3b2836eac4
Llava api (#563)
* Add llava_binaries, update all binaries to make the test

* Llava API + LlavaTest

Preliminary

* First prototype of Load + Unit Test

* Temporary run test con branch LlavaAPI

* Disable Embed test to review the rest of the test

* Restore Embedding test

* Use BatchThread to eval image embeddings

Test Threads default value to ensure it doesn´t produce problems.

* Rename test file

* Update action versions

* Test only one method, no release embeddings

* Revert "Test only one method, no release embeddings"

This reverts commit 264e176dccc9cd0be318b800ae5e102a4635d01c.

* Correct API call

* Only test llava related functionality

* Cuda and Cblast binaries

* Restore build policy

* Changes related with code review

* Add SafeHandles

* Set overwrite to upload-artifact@v4

* Revert to upload-artifact@v3

* revert to upload-artifact@v3
2024-03-13 22:10:44 +00:00
..
DecodeResult.cs Swapped `StatelessExecutor` to use `llama_decode`! 2024-01-20 21:18:35 +00:00
GGMLType.cs Added a comment on the type itself 2023-12-14 01:23:44 +00:00
GPUSplitMode.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 2024-02-01 16:35:05 +00:00
GroupDisposable.cs - Added `GroupDisposable` to dispose a collection of items all together 2023-12-14 01:23:45 +00:00
LLamaBatch.cs Mutable Logits (#586) 2024-03-10 13:56:11 +00:00
LLamaBeamView.cs Switched form using raw integers, to a `LLamaToken` struct 2024-01-02 20:47:21 +00:00
LLamaBeamsState.cs Debugging slowdown by removing some things: 2023-10-30 21:35:46 +00:00
LLamaChatMessage.cs March Binary Update (#565) 2024-03-06 15:19:42 +00:00
LLamaContextParams.cs March Binary Update (#565) 2024-03-06 15:19:42 +00:00
LLamaFtype.cs March Binary Update (#565) 2024-03-06 15:19:42 +00:00
LLamaGrammarElement.cs Improved test coverage. Discovered some issues: 2023-11-18 02:40:36 +00:00
LLamaKvCacheView.cs - Exposed KV debug view through `SafeLLamaContextHandle` 2024-02-07 16:35:39 +00:00
LLamaLogLevel.cs March Binary Update (#565) 2024-03-06 15:19:42 +00:00
LLamaModelMetadataOverride.cs March Binary Update (#565) 2024-03-06 15:19:42 +00:00
LLamaModelParams.cs Added conditional compilation code to progress_callback (in LlamaModelParams struct) so the struct plays nice with legacy NET Framework 4.8 (#593) 2024-03-11 14:36:50 +00:00
LLamaModelQuantizeParams.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 2024-02-01 16:35:05 +00:00
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. 2024-01-19 23:26:36 +00:00
LLamaPoolingType.cs March Binary Update (#565) 2024-03-06 15:19:42 +00:00
LLamaPos.cs Added increment and decrement operators to `LLamaPos` 2024-02-07 17:04:57 +00:00
LLamaRopeType.cs March Binary Update (#565) 2024-03-06 15:19:42 +00:00
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. 2024-01-19 23:26:36 +00:00
LLamaToken.cs Added a test with examples of troublesome strings from 0.9.1 2024-01-16 15:02:23 +00:00
LLamaTokenData.cs made casts to/from int explicit, fixed places affected 2024-01-02 20:57:37 +00:00
LLamaTokenDataArray.cs Classifier Free Guidance (#536) 2024-02-26 15:41:57 +00:00
LLamaTokenType.cs Assorted small changes to clean up some code warnings 2024-02-17 23:07:10 +00:00
LLamaVocabType.cs March Binary Update (#565) 2024-03-06 15:19:42 +00:00
LLavaImageEmbed.cs Llava api (#563) 2024-03-13 22:10:44 +00:00
NativeApi.BeamSearch.cs Code cleanup driven by R# suggestions: 2024-01-02 03:20:21 +00:00
NativeApi.Grammar.cs Switched form using raw integers, to a `LLamaToken` struct 2024-01-02 20:47:21 +00:00
NativeApi.LLava.cs Llava api (#563) 2024-03-13 22:10:44 +00:00
NativeApi.Load.cs Llava api (#563) 2024-03-13 22:10:44 +00:00
NativeApi.Quantize.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 2024-02-01 16:35:05 +00:00
NativeApi.Sampling.cs Classifier Free Guidance (#536) 2024-02-26 15:41:57 +00:00
NativeApi.cs March Binary Update (#565) 2024-03-06 15:19:42 +00:00
NativeLibraryConfig.cs NativeLibraryConfig: WithLogs(LLamaLogLevel) (#529) 2024-02-21 23:51:09 +00:00
RopeScalingType.cs March Binary Update (#565) 2024-03-06 15:19:42 +00:00
SafeLLamaContextHandle.cs llama_decode lock (#595) 2024-03-13 00:33:16 +00:00
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! 2024-01-31 18:01:03 +00:00
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! 2024-01-31 18:01:03 +00:00
SafeLlamaModelHandle.cs Merge pull request #438 from martindevans/cleanup_model_unnecessary_unsafe 2024-01-15 16:31:21 +00:00
SafeLlavaImageEmbedHandle.cs Llava api (#563) 2024-03-13 22:10:44 +00:00
SafeLlavaModelHandle.cs Llava api (#563) 2024-03-13 22:10:44 +00:00