baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Update CHANGELOG

Browse source
This commit is contained in:
Andrei Betlen 2023-09-13 02:50:27 -04:00
parent 8e13520796
commit 1372e4f60e
1 changed files with 32 additions and 61 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

93
CHANGELOG.md
View file

@ -9,26 +9,50 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [0.2.2] ## [0.2.2]
- Fix bug in pip install of v0.2.1 due to scikit-build-core removing all `.metal` files in the source distribution - Fix bug in pip install of v0.2.1 due to scikit-build-core removing all `.metal` files in the source distribution (see #701)
## [0.2.1] ## [0.2.1]
- Fix bug in pip install of v0.2.0 due to .git folder being included in the source distribution - Fix bug in pip install of v0.2.0 due to .git folder being included in the source distribution (see #701)
## [0.2.0] ## [0.2.0]
- Migrated to scikit-build-core for building llama.cpp from source - Migrated to scikit-build-core build system by @abetlen in #499
- Use `numpy` views for `LogitsProcessor` and `StoppingCriteria` instead of python lists by @abetlen in #499
- Drop support for end-of-life Python3.7 by @abetlen in #499
- Convert low level `llama.cpp` constants to use basic python types instead of `ctypes` types by @abetlen in #499
## [0.1.85]
- Add `llama_cpp.__version__` attribute by @janvdp in #684
- Fix low level api examples by @jbochi in #680
## [0.1.84]
- Update llama.cpp
## [0.1.83]
- Update llama.cpp
## [0.1.82]
- Update llama.cpp
## [0.1.81]
- Update llama.cpp
## [0.1.80]
- Update llama.cpp
## [0.1.79] ## [0.1.79]
### Added
- GGUF Support (breaking change requiring new model format) - GGUF Support (breaking change requiring new model format)
## [0.1.78] ## [0.1.78]
### Added
- Grammar based sampling via LlamaGrammar which can be passed to completions - Grammar based sampling via LlamaGrammar which can be passed to completions
- Make n_gpu_layers == -1 offload all layers - Make n_gpu_layers == -1 offload all layers
@ -47,92 +71,61 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [0.1.74] ## [0.1.74]
### Added
- (server) OpenAI style error responses - (server) OpenAI style error responses
## [0.1.73] ## [0.1.73]
### Added
- (server) Add rope parameters to server settings - (server) Add rope parameters to server settings
## [0.1.72] ## [0.1.72]
### Added
- (llama.cpp) Update llama.cpp added custom_rope for extended context lengths - (llama.cpp) Update llama.cpp added custom_rope for extended context lengths
## [0.1.71] ## [0.1.71]
### Added
- (llama.cpp) Update llama.cpp - (llama.cpp) Update llama.cpp
### Fixed
- (server) Fix several pydantic v2 migration bugs - (server) Fix several pydantic v2 migration bugs
## [0.1.70] ## [0.1.70]
### Fixed
- (Llama.create_completion) Revert change so that `max_tokens` is not truncated to `context_size` in `create_completion` - (Llama.create_completion) Revert change so that `max_tokens` is not truncated to `context_size` in `create_completion`
- (server) Fixed changed settings field names from pydantic v2 migration - (server) Fixed changed settings field names from pydantic v2 migration
## [0.1.69] ## [0.1.69]
### Added
- (server) Streaming requests can are now interrupted pre-maturely when a concurrent request is made. Can be controlled with the `interrupt_requests` setting. - (server) Streaming requests can are now interrupted pre-maturely when a concurrent request is made. Can be controlled with the `interrupt_requests` setting.
- (server) Moved to fastapi v0.100.0 and pydantic v2 - (server) Moved to fastapi v0.100.0 and pydantic v2
- (docker) Added a new "simple" image that builds llama.cpp from source when started. - (docker) Added a new "simple" image that builds llama.cpp from source when started.
## Fixed
- (server) performance improvements by avoiding unnecessary memory allocations during sampling - (server) performance improvements by avoiding unnecessary memory allocations during sampling
## [0.1.68] ## [0.1.68]
### Added
- (llama.cpp) Update llama.cpp - (llama.cpp) Update llama.cpp
## [0.1.67] ## [0.1.67]
### Fixed
- Fix performance bug in Llama model by pre-allocating memory tokens and logits. - Fix performance bug in Llama model by pre-allocating memory tokens and logits.
- Fix bug in Llama model where the model was not free'd after use. - Fix bug in Llama model where the model was not free'd after use.
## [0.1.66] ## [0.1.66]
### Added
- (llama.cpp) New model API - (llama.cpp) New model API
### Fixed
- Performance issue during eval caused by looped np.concatenate call - Performance issue during eval caused by looped np.concatenate call
- State pickling issue when saving cache to disk - State pickling issue when saving cache to disk
## [0.1.65] ## [0.1.65]
### Added
- (llama.cpp) Fix struct misalignment bug - (llama.cpp) Fix struct misalignment bug
## [0.1.64] ## [0.1.64]
### Added
- (llama.cpp) Update llama.cpp - (llama.cpp) Update llama.cpp
- Fix docs for seed. Set -1 for random. - Fix docs for seed. Set -1 for random.
## [0.1.63] ## [0.1.63]
### Added
- (llama.cpp) Add full gpu utilisation in CUDA - (llama.cpp) Add full gpu utilisation in CUDA
- (llama.cpp) Add get_vocab - (llama.cpp) Add get_vocab
- (llama.cpp) Add low_vram parameter - (llama.cpp) Add low_vram parameter
@ -140,59 +133,37 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [0.1.62] ## [0.1.62]
### Fixed
- Metal support working - Metal support working
- Cache re-enabled - Cache re-enabled
## [0.1.61] ## [0.1.61]
### Fixed
- Fix broken pip installation - Fix broken pip installation
## [0.1.60] ## [0.1.60]
### NOTE NOTE: This release was deleted due to a bug with the packaging system that caused pip installations to fail.
- This release was deleted due to a bug with the packaging system that caused pip installations to fail.
### Fixed
- Truncate max_tokens in create_completion so requested tokens doesn't exceed context size. - Truncate max_tokens in create_completion so requested tokens doesn't exceed context size.
- Temporarily disable cache for completion requests - Temporarily disable cache for completion requests
## [v0.1.59] ## [v0.1.59]
### Added
- (llama.cpp) k-quants support - (llama.cpp) k-quants support
- (server) mirostat sampling parameters to server - (server) mirostat sampling parameters to server
### Fixed
- Support both `.so` and `.dylib` for `libllama` on MacOS - Support both `.so` and `.dylib` for `libllama` on MacOS
## [v0.1.58] ## [v0.1.58]
### Added
- (llama.cpp) Metal Silicon support - (llama.cpp) Metal Silicon support
## [v0.1.57] ## [v0.1.57]
### Added
- (llama.cpp) OpenLlama 3B support - (llama.cpp) OpenLlama 3B support
## [v0.1.56] ## [v0.1.56]
### Added
- (misc) Added first version of the changelog - (misc) Added first version of the changelog
- (server) Use async routes - (server) Use async routes
- (python-api) Use numpy for internal buffers to reduce memory usage and improve performance. - (python-api) Use numpy for internal buffers to reduce memory usage and improve performance.
### Fixed
- (python-api) Performance bug in stop sequence check slowing down streaming. - (python-api) Performance bug in stop sequence check slowing down streaming.