Martin Evans
|
18b15184ea
|
Added logger parameter in to LLama.Web context creation
|
2 years ago |
Martin Evans
|
328022b13d
|
Fixed merge conflicts
|
2 years ago |
Martin Evans
|
7ec318aab5
|
Added logging to embedder too
|
2 years ago |
Martin Evans
|
f1e5a8f995
|
- Passing the `ILogger` through to every call of `CreateContext`
- Passing `ILogger` into executors
|
2 years ago |
Martin Evans
|
d2cf9489a0
|
Merge pull request #197 from saddam213/master
Update WebUI inline with v5.0.x
|
2 years ago |
sa_ddam213
|
952e77f97b
|
Remove old parameter
|
2 years ago |
sa_ddam213
|
4ec9aed47a
|
Revert LLamasSharp project changes
|
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
|
6e5a2e162c
|
Merge pull request #196 from martindevans/cleanup
Cleanup
|
2 years ago |
Martin Evans
|
e89ca5cc17
|
Fixed a few minor warnings
|
2 years ago |
Martin Evans
|
9daf586ba8
|
Assorted cleanup leftover after the huge change in the last PR (comments, syntax style, etc)
|
2 years ago |
Martin Evans
|
d8434ea9d6
|
Merge pull request #185 from martindevans/wip_major_api_change
Major llama.cpp API Change
|
2 years ago |
Martin Evans
|
1f8c94e386
|
Added in the `special` parameter to the tokenizer (introduced in https://github.com/ggerganov/llama.cpp/pull/3538)
|
2 years ago |
Martin Evans
|
efb0664df0
|
- Added new binaries
- Fixed stateless executor out-of-context handling
- Fixed token tests
|
2 years ago |
Martin Evans
|
8562e1b924
|
Merge pull request #193 from DVaughan/dv-update-SemanticKernel-1.0.0-beta1
Support SemanticKernel 1.0.0-beta1
|
2 years ago |
Martin Evans
|
2ad6aef185
|
Merge pull request #194 from martindevans/yet_more_tests
More Tests
|
2 years ago |
Martin Evans
|
b8f0eff080
|
- Added `GetCharCountImpl` tests, fixed handling of empty strings
- Added ifdef to remove `Deconstruct` extension on everything except `NETSTANDARD2_0`
|
2 years ago |
Martin Evans
|
45118520fa
|
- Improved coverage of `GBNFGrammarParser` up to 96%
- Covered text transforms
- Removed unnecessary non-async transforms
|
2 years ago |
Daniel Vaughan
|
10a7d68330
|
Change to nullable cast in LLamaSharpTextCompletion.
|
2 years ago |
Daniel Vaughan
|
f64a54c9c8
|
Support SemanticKernel 1.0.0-beta1
|
2 years ago |
Martin Evans
|
58ec110a7d
|
Merge pull request #192 from martindevans/GrammarRule_tests
GrammarRule Tests
|
2 years ago |
Martin Evans
|
9f694c584c
|
Further improved grammar parser test coverage (up to 92%)
|
2 years ago |
Martin Evans
|
bff41eef37
|
Added some more coverage of `GrammarRule`, checking that invalid rules are rejected
|
2 years ago |
Martin Evans
|
2a38808bca
|
- Added threads to context params, replaced all thread args with `uint?`
- Replaced all binaries
|
2 years ago |
Martin Evans
|
4e9b1f8cdc
|
- Split extension methods into separate files
|
2 years ago |
Martin Evans
|
6a7634309e
|
Merge pull request #190 from martindevans/fix/github_build
Fixed GitHub Action
|
2 years ago |
Martin Evans
|
1a94c48fb6
|
Added some parallelism to CUDA build (just set to 4 for now, no cross platform way to get it)
|
2 years ago |
Martin Evans
|
2b5bc915de
|
Removed samples from linux install
|
2 years ago |
Martin Evans
|
ed38be1040
|
added the VS integration back in for windows
|
2 years ago |
Martin Evans
|
8fba1f56a7
|
Using the old install method on Linux
|
2 years ago |
Martin Evans
|
8c63422ea9
|
Removed "visual_studio_integration", hopefully that will fix linux and not break windows
|
2 years ago |
Martin Evans
|
d48dd3a4fc
|
added sub packages to reduce how much CUDA stuff needs installing
|
2 years ago |
Martin Evans
|
6571e982e1
|
disabled `-march=native` for macos build which was causing a build failure
|
2 years ago |
Martin Evans
|
2c9519bb56
|
sped up macos build
|
2 years ago |
sa_ddam213
|
a8a498dc12
|
Fix up issues found during testing
|
2 years ago |
sa_ddam213
|
9b8de007dc
|
Propagate ILogger
|
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
|
0f03e8f1a3
|
Added workaround to LLama.Web and LLama.WebAPI
|
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
|
9a0a0ae9fe
|
Removed cloning support
|
2 years ago |
Martin Evans
|
0d40338692
|
Fixed out-of-context handling in stateless executor
|
2 years ago |
Martin Evans
|
56073e7d11
|
Merge pull request #182 from martindevans/async_stateless_eval
Async Stateless Executor
|
2 years ago |
Martin Evans
|
b306ac23dd
|
Added `Decode` method to `SafeLLamaContextHandle`
|
2 years ago |
Martin Evans
|
9e958e896b
|
safe handle for batch
|
2 years ago |
Martin Evans
|
ce1fc51163
|
Added some more native methods
|
2 years ago |
Martin Evans
|
bca55eace0
|
Initial changes to match the llama.cpp changes
|
2 years ago |
Martin Evans
|
b7379b7124
|
Moved spinner out to an extension, so it can easily be used in other examples
|
2 years ago |
Martin Evans
|
d58fcbbd13
|
Fixed antiprompt checking
|
2 years ago |