24 Commits (e89ca5cc17bf9cccdaf24e5b4ac78c0b7183e7a2)

Author SHA1 Message Date
  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 1f8c94e386 Added in the `special` parameter to the tokenizer (introduced in https://github.com/ggerganov/llama.cpp/pull/3538) 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 b306ac23dd Added `Decode` method to `SafeLLamaContextHandle` 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 daf09eae64 Skipping tokenization of empty strings (saves allocating an empty array every time) 2 years ago
  Martin Evans bba801f4b7 Added a property to get the KV cache size from a context 2 years ago
  Martin Evans 31287b5e6e Rewritten TokenToSpan/TokenToString to better fit the new way it's done in llama.cpp with a few different options: 2 years ago
  Martin Evans ebacdb666d - Moved the lower level state get/set methods onto SafeLLamaContextHandle 2 years ago
  Martin Evans a9e6f21ab8 - Creating and destroying contexts in the stateless executor, saving memory. It now uses zero memory when not inferring! 2 years ago
  Martin Evans ae8ef17a4a - Added various convenience overloads to `LLamaContext.Eval` 2 years ago
  Martin Evans 479ff57853 Renamed `EmbeddingCount` to `EmbeddingSize` 2 years ago
  Martin Evans d0a7a8fcd6 - Cleaned up disposal in LLamaContext 2 years ago
  Martin Evans f3511e390f WIP demonstrating changes to support multi-context. You can see this in use in `TalkToYourself`, along with notes on what still needs improving. 2 years ago
  Martin Evans 2b2d3af26b Moved `Eval` out of `Utils` and into `SafeLLamaContextHandle` 2 years ago
  Martin Evans 0e5e00e300 Moved `TokenToString` from Utils into `SafeLLamaContextHandle` (thin wrappers around the same method in `SafeLlamaModelHandle`) 2 years ago
  Martin Evans 2d811b2603 - Moved `GetLogits` into `SafeLLamaContextHandle` 2 years ago
  Martin Evans cd3cf2b77d - Moved tokenization from `Utils.Tokenize` into `SafeLLamaContextHandle.Tokenize`, one less thing in `Utils`. 2 years ago
  Martin Evans f16aa58e12 Updated to use the new loading system in llama (llama_state). This new system has split model weights and contexts into two separate things, allowing one set of weights to be shared between many contexts. 2 years ago
  Yaohui Liu 0958bbac2c
feat: add get-embedding api to LLamaModel. 2 years ago
  Yaohui Liu 5a79edeb51
feat: add the framework and basic usages. 2 years ago