bretello
740f3f3812
fix: set LLAMA_METAL_EMBED_LIBRARY=on on MacOS arm64 ( #1289 )
2024-03-20 12:46:09 -04:00
Douglas Hanley
19b55ad3e5
feat: use gpu backend for clip if available ( #1175 )
2024-02-11 13:53:59 -05:00
Andrei Betlen
e3941d9c67
Make building llava optional
2023-11-28 04:55:21 -05:00
Andrei Betlen
4388f33414
Set CUDA_ARCHITECTURES=OFF for windows
2023-11-10 16:32:36 -05:00
Damian Stewart
aab74f0b2b
Multimodal Support (Llava 1.5) ( #821 )
...
* llava v1.5 integration
* Point llama.cpp to fork
* Add llava shared library target
* Fix type
* Update llama.cpp
* Add llava api
* Revert changes to llama and llama_cpp
* Update llava example
* Add types for new gpt-4-vision-preview api
* Fix typo
* Update llama.cpp
* Update llama_types to match OpenAI v1 API
* Update ChatCompletionFunction type
* Reorder request parameters
* More API type fixes
* Even More Type Updates
* Add parameter for custom chat_handler to Llama class
* Fix circular import
* Convert to absolute imports
* Fix
* Fix pydantic Jsontype bug
* Accept list of prompt tokens in create_completion
* Add llava1.5 chat handler
* Add Multimodal notebook
* Clean up examples
* Add server docs
---------
Co-authored-by: Andrei Betlen <abetlen@gmail.com>
2023-11-07 22:48:51 -05:00
Andrei Betlen
b4939c2d99
Revert BUILD_NUMBER fix
2023-09-29 23:28:45 -04:00
Andrei Betlen
43f8fc371a
Potential fix for pip install bug
2023-09-29 22:24:22 -04:00
Andrei Betlen
8d75016549
Install required runtime dlls to package directory on windows
2023-09-16 14:57:49 -04:00
Andrei Betlen
dbd3a6d1ed
Fix issue installing on m1 macs
2023-09-14 18:25:44 -04:00
Andrei Betlen
e3387e4655
Add explanatory comment
2023-09-12 18:41:00 -04:00
Andrei Betlen
e65a823dc8
Update flags
2023-09-12 18:37:32 -04:00
Andrei Betlen
4cb0e35b64
string options
2023-09-12 18:35:34 -04:00
Andrei Betlen
2c3df160fb
Reorder
2023-09-12 18:29:18 -04:00
Andrei Betlen
d123129e63
fix
2023-09-12 18:25:31 -04:00
Andrei Betlen
dadfd96745
Use compiler to determine best optimizations for platform
2023-09-12 18:21:49 -04:00
Andrei Betlen
4c0787b408
Disable acceleration in macos tests only
2023-09-12 18:05:44 -04:00
Andrei Betlen
d24383eaef
Disable acceleration on macos
2023-09-12 17:58:47 -04:00
Andrei Betlen
9547a351ee
Try arm64 python
2023-09-12 17:35:07 -04:00
Andrei Betlen
010a50168c
Add tune
2023-09-12 17:20:57 -04:00
Andrei Betlen
f93fb30f5c
Set native arch flags for macos
2023-09-12 17:15:07 -04:00
Andrei Betlen
6cb77a20c6
Migrate to scikit-build-core. Closes #489
2023-07-18 18:52:29 -04:00
Andrei Betlen
c1eaef329a
Add resource destination to cmake
2023-06-10 18:11:48 -04:00
Andrei Betlen
e3542b6627
Revert "Merge pull request #350 from abetlen/migrate-to-scikit-build-core"
...
This reverts commit fb2c5f7fd9202ed4464b
2023-06-09 23:23:16 -04:00
Andrei Betlen
b025a859ae
Add full path to shared library installation path
2023-06-08 22:11:01 -04:00
Andrei Betlen
7345456779
Migrate to scikit-build-core
2023-06-08 21:49:42 -04:00
Andrei Betlen
cf6a9d6d8e
Add framework and archive destinations to cmake for macos and windows.
2023-06-07 03:42:55 -04:00
Andrei Betlen
341c50b5b0
Fix CMakeLists.txt
2023-05-16 09:07:14 -04:00
Andrei Betlen
848c83dfd0
Add FORCE_CMAKE option
2023-04-25 01:36:37 -04:00
Andrei Betlen
e611cfc56d
Build shared library with make on unix platforms
2023-04-08 02:39:17 -04:00
Andrei Betlen
88c23d04a8
Fix windows dll location issue
2023-04-06 22:44:31 -04:00
Andrei Betlen
241722c981
Quote destination
2023-04-06 22:38:53 -04:00
Andrei Betlen
02760f8fa7
Update llama.cpp and shared library build process
2023-03-23 17:01:06 -04:00
Andrei Betlen
465238b179
Updated package to build with skbuild
2023-03-23 13:54:14 -04:00
