Martin Evans
92b9bbe779
Added methods to `SafeLLamaContextHandle` for KV cache manipulation
1 year ago
Martin Evans
96c26c25f5
Merge pull request #445 from martindevans/stateless_executor_llama_decode
Swapped `StatelessExecutor` to use `llama_decode`!
1 year ago
xbotter
90815ae7d8
bump sk & km
- bump semantic kernel to 1.1.0
- bump kernel memory to 0.26
1 year ago
Martin Evans
9fe878ae1f
- Fixed example
- Growing more than double, if necessary
1 year ago
Martin Evans
a2e29d393c
Swapped `StatelessExecutor` to use `llama_decode`!
- Added `logits_i` argument to `Context.ApplyPenalty`
- Added a new exception type for `llama_decode` return code
1 year ago
Martin Evans
5b6e82a594
Improved the BatchedDecoding demo:
- using less `NativeHandle`
- Using `StreamingTokenDecoder` instead of obsolete detokenize method
1 year ago
Martin Evans
99969e538e
- Removed some unused `eval` methods.
- Added a `DecodeAsync` overload which runs the work in a task
- Replaced some `NativeHandle` usage in `BatchedDecoding` with higher level equivalents.
- Made the `LLamaBatch` grow when token capacity is exceeded, removing the need to manage token capacity externally.
1 year ago
Martin Evans
36a9335588
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
Martin Evans
42be9b136d
Switched form using raw integers, to a `LLamaToken` struct
1 year ago
Martin Evans
a408335c44
Fixed broken build on master (just removing a namespace that no longer exists)
1 year ago
dependabot[bot]
f02b0500b5
build(deps): bump Microsoft.KernelMemory.Core and Microsoft.KernelMemory.Abstractions
Bumps [Microsoft.KernelMemory.Core](https://github.com/microsoft/kernel-memory ) and [Microsoft.KernelMemory.Abstractions](https://github.com/microsoft/kernel-memory ). These dependencies needed to be updated together.
Updates `Microsoft.KernelMemory.Core` from 0.18.231209.1-preview to 0.24.231228.5
- [Release notes](https://github.com/microsoft/kernel-memory/releases )
- [Commits](https://github.com/microsoft/kernel-memory/compare/dotnet-0.18.231209.1-preview...0.24.231228.5 )
Updates `Microsoft.KernelMemory.Abstractions` from 0.18.231209.1-preview to 0.24.231228.5
- [Release notes](https://github.com/microsoft/kernel-memory/releases )
- [Commits](https://github.com/microsoft/kernel-memory/compare/dotnet-0.18.231209.1-preview...0.24.231228.5 )
---
updated-dependencies:
- dependency-name: Microsoft.KernelMemory.Core
dependency-type: direct:production
update-type: version-update:semver-minor
- dependency-name: Microsoft.KernelMemory.Abstractions
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com>
1 year ago
Martin Evans
f0d7468b22
Merge pull request #356 from xbotter/deps/sk-rc3
bump sk to 1.0.1 & km to 0.18
1 year ago
xbotter
40ac944fb5
Bump sk to 1.0.1
1 year ago
Martin Evans
b868b056f7
Added metadata overrides to `IModelParams`
1 year ago
xbotter
8766fb1b03
Merge branch 'deps/sk-rc3' of https://github.com/xbotter/LLamaSharp into deps/sk-rc3
1 year ago
xbotter
213b4be723
bump sk-1.0.0-rc4
1 year ago
xbotter
ce20b30e06
Merge branch 'SciSharp:master' into deps/sk-rc3
1 year ago
Martin Evans
bab6b65b61
Added a safe handle for LLamaKvCacheView
1 year ago
Rinne
fb75e06293
fix: output prefix of Chinese example.
1 year ago
Rinne
836f071cd0
fix: Chinese example.
1 year ago
xbotter
13a312b4ec
update sk to 1.0.0-rc3 & km to 0.18
1 year ago
Philipp Bauer
f669a4f5a7
Update the Chinese chat sample to use new ChatSession integration
1 year ago
Philipp Bauer
2cc01efdae
Merge branch 'SciSharp:master' into master
1 year ago
Martin Evans
4fc743c9ba
Merge branch 'master' into master
1 year ago
Philipp Bauer
422605d980
Re-add ChatSession examples
2 years ago
Philipp Bauer
73d1725954
Modified / updated ChatSession examples
2 years ago
Philipp Bauer
f1eac82ecc
Update target frameworks with .NET 8
2 years ago
xbotter
a2b26faa7a
🔧 Refactor chat completion implementation
- Refactored the chat completion implementation in `LLamaSharpChatCompletion.cs` to use `StatelessExecutor` instead of `InteractiveExecutor`.
- Updated the chat history prompt in `LLamaSharpChatCompletion.cs` to include a conversation between the assistant and the user.
- Modified the `HistoryTransform` class in `HistoryTransform.cs` to append the assistant role to the chat history prompt.
- Updated the constructor of `LLamaSharpChatCompletion` to accept optional parameters for `historyTransform` and `outputTransform`.
- Modified the `GetChatCompletionsAsync` and `GetChatCompletions` methods in `LLamaSharpChatCompletion.cs` to use the new `StatelessExecutor` and `outputTransform`.
- Updated the `ExtensionMethods.cs` file to include the assistant and system roles in the list of anti-prompts.
2 years ago
dependabot[bot]
36adc4af32
build(deps): bump Spectre.Console from 0.47.0 to 0.48.0
Bumps [Spectre.Console](https://github.com/spectreconsole/spectre.console ) from 0.47.0 to 0.48.0.
- [Release notes](https://github.com/spectreconsole/spectre.console/releases )
- [Commits](https://github.com/spectreconsole/spectre.console/compare/0.47.0...0.48.0 )
---
updated-dependencies:
- dependency-name: Spectre.Console
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com>
2 years ago
Rinne
605d1ddb3f
revert a change.
2 years ago
Rinne
934358a7b3
Merge branch 'master' of github.com:AsakusaRinne/LLamaSharp into fix_chinese
2 years ago
Rinne
217c67b757
fix: chinese encoding error.
2 years ago
xbotter
d1e2a4750b
🔧 Update KernelMemory configuration
- Update LLamaSharpTextEmbeddingGeneration and LLamaSharpTextGeneration
- Add Microsoft.KernelMemory.Core package reference
- Update Microsoft.KernelMemory.Abstractions package reference
2 years ago
dependabot[bot]
20a0dc7ac6
build(deps): bump Microsoft.Extensions.Logging.Console
Bumps [Microsoft.Extensions.Logging.Console](https://github.com/dotnet/runtime ) from 7.0.0 to 8.0.0.
- [Release notes](https://github.com/dotnet/runtime/releases )
- [Commits](https://github.com/dotnet/runtime/compare/v7.0.0...v8.0.0 )
---
updated-dependencies:
- dependency-name: Microsoft.Extensions.Logging.Console
dependency-type: direct:production
update-type: version-update:semver-major
...
Signed-off-by: dependabot[bot] <support@github.com>
2 years ago
Rinne
c94aeabc4b
Merge pull request #307 from xbotter/sm-default-config
Add DefaultInferenceParams to Kernel Memory
2 years ago
xbotter
286904920b
update DefaultInferenceParams in WithLLamaSharpDefaults
2 years ago
xbotter
1056e13414
fix examples
2 years ago
xbotter
15db931a66
bump semantic kernel 1.0.0-beta8
2 years ago
Martin Evans
9905baa7c4
Merge pull request #300 from martindevans/minor_demos_cleanup
Minor cleanup on example code
2 years ago
Martin Evans
1dd4c6ab7a
Merge pull request #296 from xbotter/deps/sk_1.0.0-beta6
bump semantic kernel to 1.0.0-beta-6
2 years ago
Martin Evans
479779e908
Some minor cleanup on example code:
- Removed special case for exit
- Added a wait at the end of batched decoding
2 years ago
xbotter
6c31f69720
bump semantic kernel to 1.0.0-beta-6
2 years ago
xbotter
521e36903c
🔀 Remove unused code and update examples
- Renamed files and updated namespaces in Examples folder.
- Moved files from NewVersion folder to Examples folder.
- Removed TestRunner.cs file.
- Updated Runner.cs to include new examples.
- Update Program.cs to use the new Runner class instead of NewVersionTestRunner
- Update LLama.Examples namespace in Program.cs
- Update await NewVersionTestRunner.Run() in Program.cs to await Runner.Run()
2 years ago
Martin Evans
a9d1f6cb47
- Renamed `NativeLibraryConfig.Default` to `NativeLibraryConfig.Instance`. It's not default any more as soon as you call `WithX`!
- using `Lazy<T>` to initialize it automatically.
- Added in `AVX512` support for all dotnet versions (but not autodetected).
- Added in AVX version auto detection.
2 years ago
Yaohui Liu
d7675f7936
Merge branch 'master' of github.com:AsakusaRinne/LLamaSharp into cuda_detection
2 years ago
Yaohui Liu
cb5fb210b1
feat: optimize apis for cuda feature detection.
2 years ago
SignalRT
fb95bbb4e0
Merge remote-tracking branch 'upstream/master' into RuntimeDetection
2 years ago
SignalRT
6de8d6219a
Change SemanticKernel version to beta1 on Examples
2 years ago
Rinne
14b5994c93
Merge branch 'master' into add_kernel_memory_pkg
2 years ago
SignalRT
5fe721bdbe
Revert "Merge branch 'pr/268' into RuntimeDetection"
This reverts commit 091b8d58b3502a99b3bfbec9db457c92cc736beb, reversing
changes made to 9b2ca9cf8e .
2 years ago