Louis
89653eda08
fix: disabling Vulkan causes users to be stuck in GPU-accelerated mode ( #2578 )
2024-04-02 17:35:15 +07:00
Louis
784af8cf55
fix: model recommendation label is not based on VRAM ( #2517 )
2024-03-27 18:21:33 +07:00
Louis
489e8aab24
Sync release 0.4.9 to dev ( #2407 )
...
* fix: move tensorrt executable to engine (#2400 )
* fix: move tensorrt executable to engine
Signed-off-by: James <james@jan.ai>
* some update
Signed-off-by: hiro <hiro@jan.ai>
* chore: bump tensorrt version
* fix: wrong destroy path
* fix: install extensions in parallel
* chore: update path for tensorrt engine (#2404 )
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
---------
Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
* Release/v0.4.9 (#2421 )
* fix: turn off experimental settings should also turn off quick ask (#2411 )
* fix: app glitches 1s generating response before starting model (#2412 )
* fix: disable experimental feature should also disable vulkan (#2414 )
* fix: model load stuck on windows when can't get CPU core count (#2413 )
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
* feat: TensorRT-LLM engine update support (#2415 )
* fix: engine update
* chore: add remove prepopulated models
Signed-off-by: James <james@jan.ai>
* update tinyjensen url
Signed-off-by: James <james@jan.ai>
* update llamacorn
Signed-off-by: James <james@jan.ai>
* update Mistral 7B Instruct v0.1 int4
Signed-off-by: James <james@jan.ai>
* update tensorrt
Signed-off-by: James <james@jan.ai>
* update
Signed-off-by: hiro <hiro@jan.ai>
* update
Signed-off-by: James <james@jan.ai>
* prettier
Signed-off-by: James <james@jan.ai>
* update mistral config
Signed-off-by: James <james@jan.ai>
* fix some lint
Signed-off-by: James <james@jan.ai>
---------
Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>
* Tensorrt LLM disable turing support (#2418 )
Co-authored-by: Hien To <tominhhien97@gmail.com>
* chore: add prompt template tensorrtllm (#2375 )
* chore: add prompt template tensorrtllm
* Add Prompt template for mistral and correct model metadata
---------
Co-authored-by: Hien To <tominhhien97@gmail.com>
* fix: correct tensorrt mistral model.json (#2419 )
---------
Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>
Co-authored-by: hiento09 <136591877+hiento09@users.noreply.github.com>
Co-authored-by: Hien To <tominhhien97@gmail.com>
---------
Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: NamH <NamNh0122@gmail.com>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>
Co-authored-by: hiento09 <136591877+hiento09@users.noreply.github.com>
Co-authored-by: Hien To <tominhhien97@gmail.com>
2024-03-19 12:20:09 +07:00
hiro
926f19bd9b
feat: Add nitro vulkan to support AMD GPU/ APU and Intel Arc GPU ( #2056 )
...
* feat: add vulkan support on windows and linux
* fix: correct vulkan settings
* fix: gpu settings and enable Vulkan support
* fix: vulkan support 1 device at a time only
* inference-nitro-extension add download vulkaninfo
---------
Co-authored-by: Louis <louis@jan.ai>
Co-authored-by: Hien To <tominhhien97@gmail.com>
2024-02-22 11:19:36 +07:00
Faisal Amir
6f520b4534
feat: imporve UI/UX gpu acceleration feature ( #1990 )
2024-02-13 15:36:42 +07:00
hiento09
4471b2c941
feat: User Selectable GPUs and GPU-based Model Recommendations ( #1730 )
2024-02-06 17:31:46 +07:00
NamH
8151ef0313
feat: add factory reset feature ( #1750 )
...
* feat(FactoryReset): add factory reset feature
Signed-off-by: nam <namnh0122@gmail.com>
Signed-off-by: James <james@jan.ai>
Co-authored-by: Faisal Amir <urmauur@gmail.com>
Co-authored-by: James <james@jan.ai>
2024-01-31 13:23:48 +07:00
Louis
0e48be67e8
feat: support multiple model binaries ( #1659 )
...
* feat: Support multiple model binaries
* fix: Update downloadModel with multiple binaries handler
* feat: Add 3 models with multiple binaries
* chore: fix model download
* fix: model file lookup & model path
* chore: add .prettierrc
* chore: refactor docs
* chore: bump model version
* fix(capybara): add filename
* fix(codeninja): add file name + llama model path
* fix(default): add llama model path
* fix(deepseek coder): add filename
* fix(deepseek 33B): add filename
* fix(dolphin mixtral): add filename
* fix(llama2-chat): add filename
* fix(llama2-70B): add filename
* fix(mistral 7b): add filename + model path
* fix(bakllava): correct size model
* fix(llava-7b): correct size model
* fix(llava-13b): correct size model
* fix(mixtral-8x7b): add file name + modelpath
* fix(noramaid-7b): add file name + modelpath
* fix(openchat-7b): add file name + modelpath
* fix(openhermes-7b): add file name + modelpath
* fix(phi2-3b): add file name + modelpath
* fix(phind): add file name + modelpath
* fix(solarslerp): add file name + modelpath
* fix(starling): add file name + modelpath
* fix(stealth): add file name + modelpath
* fix(tinyllama): add file name + modelpath
* fix(trinity): add file name + modelpath
* fix(tulu): add file name + modelpath
* fix(wizardcoder): add file name + modelpath
* fix(yi): add file name + modelpath
* update from source -> sources
Signed-off-by: James <james@jan.ai>
---------
Signed-off-by: James <james@jan.ai>
Co-authored-by: hiro <vuonghoainam.work@gmail.com>
Co-authored-by: hahuyhoang411 <hahuyhoanghhh41@gmail.com>
Co-authored-by: James <james@jan.ai>
2024-01-25 14:05:33 +07:00
hiento09
1ec8174700
Feature GPU detection for Jan on Windows and Linux ( #1242 )
...
* Add js function to generate gpu and cuda detection
* inference nitro manage via json file instead of bash and bat script
* Add /usr/lib/x86_64-linux-gnu/ to linux check gpu
* chore: add CPU - GPU toggle
* correct file path
* fix: exist file sync check
* fix: get resources path
* Fix error jan/engines create existed error
* Seting sync to file
* Fix error show notification for GPU
* Set notify default to true
---------
Co-authored-by: Hien To <tominhhien97@gmail.com>
Co-authored-by: Louis <louis@jan.ai>
2023-12-29 15:56:36 +07:00
