Martin Evans
|
6a4cd506bd
|
Added a safe `TensorSplitsCollection` to the params which prevents incorrectly setting the `tensor_splits` collection
|
2 years ago |
sa_ddam213
|
b4b4000342
|
Merge branch 'master' into upstream_master
# Conflicts:
# LLama.Web/Common/ModelOptions.cs
# LLama.Web/Services/ConnectionSessionService.cs
# LLama/LLamaStatelessExecutor.cs
# LLama/LLamaWeights.cs
|
2 years ago |
Martin Evans
|
2a38808bca
|
- Added threads to context params, replaced all thread args with `uint?`
- Replaced all binaries
|
2 years ago |
sa_ddam213
|
e2a17d6b6f
|
Refactor conflicting object name SessionOptions
|
2 years ago |
sa_ddam213
|
44f1b91c29
|
Update Web to support version 0.5.1
|
2 years ago |
sa_ddam213
|
c9108f8311
|
Add service for managing Models and Model Contexts
|
2 years ago |
Martin Evans
|
669ae47ef7
|
- Split parameters into two interfaces
- params contains a list of loras, instead of just one
|
2 years ago |
Martin Evans
|
bca55eace0
|
Initial changes to match the llama.cpp changes
|
2 years ago |
Martin Evans
|
2056078aef
|
Initial changes required for GGUF support
|
2 years ago |
Martin Evans
|
93f24f8a51
|
Switched to properly typed `Encoding` property
|
2 years ago |
Martin Evans
|
759ae26f36
|
Merge branch 'master' into grammar_basics
|
2 years ago |
Martin Evans
|
a9e6f21ab8
|
- Creating and destroying contexts in the stateless executor, saving memory. It now uses zero memory when not inferring!
- Passing encoding in the `IModelParams`, which reduces how often encoding needs to be passed around
|
2 years ago |
Martin Evans
|
64416ca23c
|
- Created a slightly nicer way to create grammar (from `IReadOnlyList<IReadOnlyList<LLamaGrammarElement>>`)
- Integrated grammar into sampling
- Added a test for the grammar sampling
|
2 years ago |
Martin Evans
|
2c933c57a1
|
Fixed ModelOptions in Web project
|
2 years ago |
sa_ddam213
|
bac9cba01a
|
InferenceParams abstractions
|
2 years ago |
sa_ddam213
|
2a04e31b7d
|
ModelParams abstraction
|
2 years ago |
sa_ddam213
|
3fec7a63c7
|
Add Instruct and Stateless support
|
2 years ago |
sa_ddam213
|
d9fbd56f10
|
Strongly type connection status
|
2 years ago |