Faisal Amir
daa7c0ca21
feat: better hardware setting ( #4471 )
...
* feat: better hardware setting
* chore: update layout
* feat: better hardware setting
* chore: fix title section
* chore: added hardware engine management
* chore: integrate gpus and enable set gpu activate
* chore: update calculate ram and vram
* chore: update calulate vram and ram used
* fix: set active gpus
* chore: fix progress bar spacing
* chore: always update cache vram gpu
* chore: update cpu usage percentage
* chore: fix type usage cpu
* chore: update ram cpus usage getsystemmonitor from new api harware engine management system
* test: update test case data using hardware management extension
* chore: resolve conflict lock json
* chore: cleanup app services
* chore: update type OperationSystemInfo
* chore: update app service
* chore: show list gpus on system monitor
* chore: remove monitoring extension
* chore: update test case app service
* chore: remove unused hooks useGpusSetting
* chore: remove monitor from shource index
* chore: fix test core
* chore: update gpu and cpu info on engine management ext
* chore: fix app service test
* chore: update test appService include cpu info
* chore: filter gpus show or hide on system monitor based activated gpu
* chore: remove unused run_mode
* chore: remove tensort
* chore: update check gpu run_mode
* chore: handle undefined gpus
* chore: cleanup PR
* chore: cleanup process node error
* chore: fix type
2025-02-03 22:01:08 +07:00
Louis
713926e68c
chore: attempt to stop model before switching engine variant
2025-01-16 16:18:32 +07:00
Louis
687b034b06
fix: file symlink does not work on windows for cuda dependencies
2025-01-16 16:04:28 +07:00
Louis
a4649fa9cc
chore: bump engine version to 0.1.46
2025-01-16 15:26:15 +07:00
Louis
f5e2712172
chore: symlink dll should be type file instead of junction
2025-01-16 13:25:27 +07:00
Louis
ae7a6c5d64
chore: update symbolic type
2025-01-16 12:36:07 +07:00
Faisal Amir
2a0601f75a
feat: remote engine management ( #4364 )
...
* feat: remote engine management
* chore: fix linter issue
* chore: remove unused imports
* fix: populate engines, models and legacy settings (#4403 )
* fix: populate engines, models and legacy settings
* chore: legacy logics update configured remote engine
* fix: check exist path before reading
* fix: engines and models persist - race condition
* chore: update issue state
* test: update test cases
* chore: bring back Cortex extension settings
* chore: setup button gear / plus based apikey
* chore: fix remote engine from welcome screen
* chore: resolve linter issue
* chore: support request headers template
* chore: update engines using header_template instead of api_key_template
* chore: update models on changes
* fix: anthropic response template
* chore: fix welcome screen and debounce update value input
* chore: update engines list on changes
* chore: update engines list on change
* chore: update desc form add modal remote engines
* chore: bump cortex version to latest RC
* chore: fix linter
* fix: transform payload of Anthropic and OpenAI
* fix: typo
* fix: openrouter model id for auto routing
* chore: remove remote engine URL setting
* chore: add cohere engine and model support
* fix: should not clean on app launch - models list display issue
* fix: local engine check logic
* chore: bump app version to latest release 0.5.13
* test: fix failed tests
---------
Co-authored-by: Louis <louis@jan.ai>
2025-01-14 17:29:56 +07:00
Louis
d2717fb8df
fix: load model fail on windows
2025-01-12 16:10:37 +07:00
Louis
b4d2176280
Merge pull request #4408 from janhq/main
...
Sync release 0.5.13 into dev
2025-01-06 21:01:49 +07:00
Louis
27e40c35d8
chore: add cpu_threads settings in cortex extension
2025-01-02 13:03:16 +07:00
Louis
b8bd846744
chore: refactor extensions build script for optimization
2024-12-30 22:10:48 +07:00
Faisal Amir
a6a0cb325b
feat: local engine management ( #4334 )
...
* feat: local engine management
* chore: move remote engine into engine page instead extension page
* chore: set default engine from extension
* chore: update endpoint update engine
* chore: update event onEngineUpdate
* chore: filter out engine download
* chore: update version env
* chore: select default engine variant base on user device specs
* chore: symlink engine variants
* chore: rolldown.config in mjs format
* chore: binary codesign
* fix: download state in footer bar and variant status
* chore: update yarn.lock
* fix: rimraf failure
* fix: setup-node@v3 for built-in cache
* fix: cov pipeline
* fix: build syntax
* chore: fix build step
* fix: create engines folder on launch
* chore: update ui delete engine variant with modal confirmation
* chore: fix linter
* chore: add installing progress for Local Engine download
* chore: wording
---------
Co-authored-by: Louis <louis@jan.ai>
2024-12-30 17:27:51 +07:00
Louis
fb0a916c50
fix: 4155 - Queue up health check on server restarting
2024-12-03 16:17:46 +07:00
Louis
541a37b8f1
fix: 4171 - Model loading gets stuck on stop
2024-12-02 14:04:13 +07:00
Louis
ad8484533d
Merge pull request #4132 from janhq/fix/4094-gpu-mode-not-working-after-first-factory-reset
...
fix: 4094 - gpu mode toggle on by default but not affect for the first time launch
2024-11-26 23:46:06 +07:00
Louis
3854d43e8a
fix: should queue engine set on changes
2024-11-26 22:58:30 +07:00
Louis
2478cf7bc3
Merge pull request #4130 from janhq/chore/4123-update-default-engine-request-body
...
feat: update Jan’s client request to adapt API changes from Cortex
2024-11-26 21:38:14 +07:00
Louis
d55b1dd2f8
fix: 4094 - gpu mode toggle on by default but not affect for the first time launch
2024-11-26 19:50:23 +07:00
Louis
638dbf178e
fix: 4012 - active model should be gone as soon as cortex.cpp server is killed
2024-11-26 19:03:26 +07:00
Louis
1108e6c221
test: correct test cases
2024-11-26 15:25:26 +07:00
Louis
f709c7723f
fix: factory reset hang on wiping data
2024-11-21 23:10:48 +07:00
Louis
33bfd0eed8
fix: disable timeout on model load
2024-11-20 20:39:43 +07:00
Louis
239e5f52e8
fix: force vision models to run with legacy settings
2024-11-20 12:43:10 +07:00
Louis
10e1201083
Merge pull request #4049 from janhq/fix/openai-o1-model-parameters
...
fix: correct OpenAI o1 model parameters
2024-11-20 01:09:58 +07:00
Louis
0b3847a8b1
chore: ensure server is started before letting other requests go thru
2024-11-19 23:45:08 +07:00
Louis
af20587846
fix: handle symlink model import failure - fallback to legacy model run
2024-11-19 22:39:35 +07:00
Louis
bd850fb357
chore: reduce destroy attempts
2024-11-19 13:27:49 +07:00
Louis
363008d37f
fix: model import edge cases
2024-11-19 11:44:19 +07:00
Louis
7a084b6589
Merge pull request #4040 from janhq/fix/rerender-component
...
chore: refactor rerender components
2024-11-18 20:55:22 +07:00
Louis
e9fd7f4554
fix: models load
2024-11-18 18:22:09 +07:00
Louis
f75dc662ee
chore: reduce app launch time
2024-11-18 15:58:15 +07:00
Louis
6f066357ed
chore: bump new engine version 0.1.39 and get rid of dangling process
2024-11-16 16:06:37 +07:00
Louis
a38715f18a
fix: should queue health check and default engine set before starting model
2024-11-14 23:51:51 +07:00
Louis
a15d92dbdc
feat: integrates cortex.cpp engine variants
2024-11-14 21:09:44 +07:00
Louis
8053ff9eb8
fix: attempt to establish the WebSocket connection on a connection issue
2024-11-13 15:14:14 +07:00
Louis
1bd58e1327
fix: shift model events subscription to cortex
2024-11-12 15:46:14 +07:00
Louis
0847b32e87
fix: an edge case when start a model with relative model path
2024-11-07 14:29:27 +07:00
Louis
ced44973b8
chore: queue server start and model load
2024-11-07 12:06:46 +07:00
Louis
e41bcffcef
fix: export PATH env to engine destination folder to have additional dlls scoped
2024-11-07 10:10:05 +07:00
Louis
56e35df84d
chore: clean dangling process on exit and relaunch
2024-11-06 13:34:11 +07:00
Louis
1ab02b706f
fix: model import symlink
2024-11-04 15:37:19 +07:00
Louis
a466bbca38
chore: update legacy tensorrt-llm download and run
2024-11-04 15:37:19 +07:00
Louis
2c11caf87e
chore: shared cuda dependencies
2024-11-04 15:37:18 +07:00
Louis
3643c8866e
fix: correct model settings on startup and strip down irrelevant model parameters
2024-11-04 15:37:18 +07:00
Louis
5f075c8554
fix: prebundle cudart and cublas
2024-11-04 15:37:18 +07:00
Louis
dc87f37a9b
fix: package cortex.cpp engines and cuda on windows
2024-11-04 15:37:17 +07:00
Louis
a0e2f16a3b
chore: binary naming convention - following llama.cpp release
2024-11-04 15:37:17 +07:00
Louis
03333cc4c2
fix: onboarding should cover cortex models - debounce reduce model reload - rename cortex binary name
2024-11-04 15:37:17 +07:00
Louis
40957f7686
fix: model reload state - reduce model unload events emit
2024-11-04 15:37:15 +07:00
Louis
03e15fb70f
feat: sync model hub and download progress from cortex.cpp
2024-11-04 15:37:14 +07:00
