1074 Commits (c7d0dc915aae3d38d6adeeb22cfbff5cadfaf770)
 

Author SHA1 Message Date
  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 1 year ago
  Martin Evans 174f21a385 0.10.0 1 year ago
  Martin Evans 633727bb73
Merge pull request #511 from martindevans/fixed_release_minor 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 1 year ago
  Martin Evans 968e1e464a
Merge pull request #507 from martindevans/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 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 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. 1 year ago
  Martin Evans ea12ff4e07
Merge pull request #502 from vikramvee/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). 1 year ago
  vikramvee ebd853fede Updated Examples 1 year ago
  Martin Evans 859160d6f7
Merge pull request #501 from martindevans/LLamaPos_inc_dec 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 1 year ago
  Martin Evans a8f9262b7f
Merge pull request #499 from martindevans/better_batch_processing 1 year ago
  Martin Evans c5146bac23 - Exposed KV debug view through `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 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 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 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 1 year ago
  Jason Couture a101224c34 Disable SHA256 check 1 year ago
  Martin Evans 0592164dc3
Merge pull request #489 from jasoncouture/clblast_nuget 1 year ago
  Jason Couture 1f45bae2cf
Update compile.yml 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 1 year ago
  Martin Evans d4f3f642c3
Merge pull request #488 from jasoncouture/concurrency_limit 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 1 year ago
  Martin Evans 7dbaed2d3b
Update README.md 1 year ago
  Martin Evans dfac029dde
Merge pull request #485 from zsogitbe/master 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 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 1 year ago