Martin Evans
c7d0dc915a
Assorted small changes to clean up some code warnings
1 year ago
Martin Evans
9bc129e252
Merge pull request #512 from martindevans/updated_version
Release 0.10.0
1 year ago
Martin Evans
174f21a385
0.10.0
1 year ago
Martin Evans
633727bb73
Merge pull request #511 from martindevans/fixed_release_minor
Fixed Minor Release Script
1 year ago
Martin Evans
69a74bb053
Commented back in the line that pushes to nuget
1 year ago
Martin Evans
d03c1a9201
Merge pull request #503 from martindevans/batched_executor_again
Introduced a new `BatchedExecutor`
1 year ago
Martin Evans
968e1e464a
Merge pull request #507 from martindevans/normalize_embeddings
Normalize Embeddings
1 year ago
Martin Evans
d47b6afe4d
Normalizing embeddings in `LLamaEmbedder`. As is done in llama.cpp: 2891c8aa9a/examples/embedding/embedding.cpp (L92)
1 year ago
Martin Evans
a5eba9463f
Merge pull request #505 from SciSharp/dependabot/nuget/Microsoft.NET.Test.Sdk-17.9.0
build(deps): bump Microsoft.NET.Test.Sdk from 17.8.0 to 17.9.0
1 year ago
Martin Evans
e9d9042576
Added `Divide` to `KvAccessor`
1 year ago
Martin Evans
1cc463b9b7
Added a finalizer to `BatchedExecutor`
1 year ago
dependabot[bot]
58b6b927c6
build(deps): bump Microsoft.NET.Test.Sdk from 17.8.0 to 17.9.0
Bumps [Microsoft.NET.Test.Sdk](https://github.com/microsoft/vstest ) from 17.8.0 to 17.9.0.
- [Release notes](https://github.com/microsoft/vstest/releases )
- [Changelog](https://github.com/microsoft/vstest/blob/main/docs/releases.md )
- [Commits](https://github.com/microsoft/vstest/compare/v17.8.0...v17.9.0 )
---
updated-dependencies:
- dependency-name: Microsoft.NET.Test.Sdk
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com>
1 year ago
Martin Evans
0c2cff0e1c
Added a Finalizer for `Conversation` in case it is not correctly disposed.
1 year ago
Martin Evans
949861a581
- Added a `Modify` method to `Conversation`. This grants **temporary** access to directly modify the KV cache.
- Re-implmented `Rewind` as an extension method using `Modify` internally
- Implemented `ShiftLeft`, which shifts everything over except for some starting tokens. This is the same as the `StatelessExecutor` out-of-context handling.
- Starting batch at epoch 1, this ensures that conversations (starting at zero) are below the current epoch. It also means `0` can always be used as a value guaranteed to be below the current epoch.
1 year ago
Martin Evans
ea12ff4e07
Merge pull request #502 from vikramvee/Examples
Updated Examples
1 year ago
Martin Evans
b0acecf080
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).
Conversations can be "forked", to create a copy of a conversation at a given point. This allows e.g. prompting a conversation with a system prefix just once and then forking it again and again for each individual conversation. Conversations can also be "rewound" to an earlier state.
Added two new examples, demonstrating forking and rewinding.
1 year ago
vikramvee
ebd853fede
Updated Examples
1 year ago
Martin Evans
859160d6f7
Merge pull request #501 from martindevans/LLamaPos_inc_dec
Added increment and decrement operators to `LLamaPos`
1 year ago
Martin Evans
90915c5a99
Added increment and decrement operators to `LLamaPos`
1 year ago
Martin Evans
82c471eac4
Merge pull request #500 from martindevans/improved_kv_cache_methods
Small KV Cache Handling Improvements
1 year ago
Martin Evans
a8f9262b7f
Merge pull request #499 from martindevans/better_batch_processing
Using `AddRange` in `LLamaEmbedder`
1 year ago
Martin Evans
c5146bac23
- Exposed KV debug view through `SafeLLamaContextHandle`
- Added `KvCacheSequenceDivide`
- Moved count tokens/cells methods to `SafeLLamaContextHandle`
1 year ago
Martin Evans
744758f110
Using `AddRange` in `LLamaEmbedder`
1 year ago
Martin Evans
5d80a56d11
Merge pull request #496 from martindevans/smaller_unit_test_model
Smaller Unit Test Model
1 year ago
Martin Evans
418345cbaf
limited parallelism of CI jobs
1 year ago
Martin Evans
df38d73c79
Switched to `Q3_K_S` for unit test model, instead of `Q4`. This is almost 1gb smaller, and _may_ make the macos tests less flakey.
1 year ago
Martin Evans
ac7faa0f93
Merge pull request #495 from martindevans/quantise_new_formats
Added new file types to quantisation
1 year ago
Martin Evans
c7103e86e4
Added new file types to quantisation
1 year ago
Martin Evans
17385e12b6
Merge pull request #479 from martindevans/update_binaries_feb_2024
Update binaries feb 2024
1 year ago
Martin Evans
21bdecd049
Merge branch 'update_binaries_feb_2024' of github.com:martindevans/LLamaSharp into update_binaries_feb_2024
1 year ago
Martin Evans
bac40a3b7a
Added new binaries, from this run: https://github.com/SciSharp/LLamaSharp/actions/runs/7792319886
1 year ago
Martin Evans
0e2521cff4
Merge pull request #493 from jasoncouture/remove_sha256_check
Disable SHA256 check
1 year ago
Jason Couture
a101224c34
Disable SHA256 check
1 year ago
Martin Evans
0592164dc3
Merge pull request #489 from jasoncouture/clblast_nuget
Create nuspec for OpenCL
1 year ago
Jason Couture
1f45bae2cf
Update compile.yml
Fix SHA256 hash path
1 year ago
Jason Couture
c963b051e2
Add nuspec for OpenCL (CLBLAST)
1 year ago
Martin Evans
d468df08d6
Merge pull request #487 from jasoncouture/clblast_linux
CLBlast for linux
1 year ago
Martin Evans
d4f3f642c3
Merge pull request #488 from jasoncouture/concurrency_limit
Only allow one build in parallel per ref
1 year ago
Jason Couture
bfe3ad50aa
Only allow one build in parallel per ref
1 year ago
Jason Couture
f7a6eaa49f
Cancel previous builds when a new build is started, due to how expensive this build is.
1 year ago
Jason Couture
277175af4d
CLBlast for linux
This builds CLBLAST support for linux, and makes sure to copy the
clblast shared library on both windows and linux to the artifacts.
1 year ago
Martin Evans
7dbaed2d3b
Update README.md
1 year ago
Martin Evans
dfac029dde
Merge pull request #485 from zsogitbe/master
KernelMemory EmbeddingMode bug correction
1 year ago
Zoli Somogyi
f578fcafa3
KernelMemory EmbeddingMode bug correction
1 year ago
Martin Evans
765c697f77
Fixed number type
1 year ago
Martin Evans
b2e815d51e
Updated all binaries (from this run: https://github.com/SciSharp/LLamaSharp/actions/runs/7746303349 )
1 year ago
Martin Evans
2323988cc7
Merge pull request #478 from martindevans/fixed_artifact_paths
Updated download-artifact to v4
1 year ago
Martin Evans
b5674ead97
Updated download-artifact to v4
1 year ago
Martin Evans
15a98b36d8
Updated everything to work with llama.cpp ce32060198
1 year ago
Martin Evans
48798837fb
Merge pull request #477 from martindevans/updated_cuda_toolkit
Updated compile.yml to use `Jimver/cuda-toolkit@v0.2.14`
1 year ago