scisharp
/
LLamaSharp
Not watched
1
0
Fork 0
Code
Releases 17 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
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.
1069 Commits
8 Branches
333 MB
32 Download
 
 
 
 
 
 
Tree: d03c1a9201
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'd03c1a9201'
${ noResults }
LLamaSharp/LLama
Martin Evans d03c1a9201
Merge pull request #503 from martindevans/batched_executor_again 		1 year ago
..
Abstractions Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
Batched Added `Divide` to `KvAccessor` 1 year ago
Common Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
Exceptions Swapped `StatelessExecutor` to use `llama_decode`! 1 year ago
Extensions Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
Grammars Code cleanup driven by R# suggestions: 1 year ago
Native Added `Divide` to `KvAccessor` 1 year ago
Sampling Created a new `BatchedExecutor` which processes multiple "Conversations" in one single inference batch. This is faster, even when the conversations are unrelated, and is much faster if the conversations share some overlap (e.g. a common system prompt prefix). 1 year ago
runtimes Merge pull request #479 from martindevans/update_binaries_feb_2024 1 year ago
AntipromptProcessor.cs Make AntipromptProcessor public 2 years ago
AssemblyAttributes.cs - Created a higher level `Grammar` class which is immutable and contains a list of grammar rules. This is the main "entry point" to the grammar system. 2 years ago
ChatSession.cs Rebuild ChatSession class 1 year ago
GlobalSuppressions.cs - Created a higher level `Grammar` class which is immutable and contains a list of grammar rules. This is the main "entry point" to the grammar system. 2 years ago
LLamaContext.cs Created a new `BatchedExecutor` which processes multiple "Conversations" in one single inference batch. This is faster, even when the conversations are unrelated, and is much faster if the conversations share some overlap (e.g. a common system prompt prefix). 1 year ago
LLamaEmbedder.cs Normalizing embeddings in `LLamaEmbedder`. As is done in llama.cpp: https://github.com/ggerganov/llama.cpp/blob/2891c8aa9af17f4ff636ff3868bc34ff72b56e25/examples/embedding/embedding.cpp#L92 1 year ago
LLamaExecutorBase.cs Updated everything to work with llama.cpp ce32060198b7e2d6a13a9b8e1e1369e3c295ae2a 1 year ago
LLamaInstructExecutor.cs Created a new `BatchedExecutor` which processes multiple "Conversations" in one single inference batch. This is faster, even when the conversations are unrelated, and is much faster if the conversations share some overlap (e.g. a common system prompt prefix). 1 year ago
LLamaInteractExecutor.cs Created a new `BatchedExecutor` which processes multiple "Conversations" in one single inference batch. This is faster, even when the conversations are unrelated, and is much faster if the conversations share some overlap (e.g. a common system prompt prefix). 1 year ago
LLamaQuantizer.cs Added new file types to quantisation 1 year ago
LLamaSharp.Runtime.targets Use llama instead of libllama in `[DllImport]` 1 year ago
LLamaSharp.csproj build(deps): bump System.Text.Json from 8.0.0 to 8.0.1 1 year ago
LLamaStatelessExecutor.cs Fixed build error caused by extra unnecessary parameter 1 year ago
LLamaTransforms.cs - Improved coverage of `GBNFGrammarParser` up to 96% 2 years ago
LLamaWeights.cs Improved the BatchedDecoding demo: 1 year ago
StreamingTokenDecoder.cs Fixed decoding of large tokens (over 16 bytes) in streaming text decoder 1 year ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

C#/.NET上易用的LLM高性能推理框架，支持LLaMA和LLaVA系列模型。

C# Text Metal JavaScript HTML+Razor other