Release cut 0.4.9

* fix: move tensorrt executable to engine

Signed-off-by: James <[email protected]>

* some update

Signed-off-by: hiro <[email protected]>

* chore: bump tensorrt version

* fix: wrong destroy path

* fix: install extensions in parallel

* chore: update path for tensorrt engine (#2404)

Signed-off-by: James <[email protected]>
Co-authored-by: James <[email protected]>

---------

Signed-off-by: James <[email protected]>
Signed-off-by: hiro <[email protected]>
Co-authored-by: James <[email protected]>
Co-authored-by: hiro <[email protected]>
Co-authored-by: Louis <[email protected]>

* 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 <[email protected]>
Co-authored-by: James <[email protected]>

* feat: TensorRT-LLM engine update support (#2415)

* fix: engine update

* chore: add remove prepopulated models

Signed-off-by: James <[email protected]>

* update tinyjensen url

Signed-off-by: James <[email protected]>

* update llamacorn

Signed-off-by: James <[email protected]>

* update Mistral 7B Instruct v0.1 int4

Signed-off-by: James <[email protected]>

* update tensorrt

Signed-off-by: James <[email protected]>

* update

Signed-off-by: hiro <[email protected]>

* update

Signed-off-by: James <[email protected]>

* prettier

Signed-off-by: James <[email protected]>

* update mistral config

Signed-off-by: James <[email protected]>

* fix some lint

Signed-off-by: James <[email protected]>

---------

Signed-off-by: James <[email protected]>
Signed-off-by: hiro <[email protected]>
Co-authored-by: James <[email protected]>
Co-authored-by: hiro <[email protected]>

* Tensorrt LLM disable turing support (#2418)

Co-authored-by: Hien To <[email protected]>

* 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 <[email protected]>

* fix: correct tensorrt mistral model.json (#2419)

---------

Signed-off-by: James <[email protected]>
Signed-off-by: hiro <[email protected]>
Co-authored-by: Louis <[email protected]>
Co-authored-by: James <[email protected]>
Co-authored-by: hiro <[email protected]>
Co-authored-by: hiento09 <[email protected]>
Co-authored-by: Hien To <[email protected]>

# Conflicts:
#	core/src/browser/core.ts
#	core/src/browser/extensions/monitoring.ts
#	core/src/browser/fs.ts
#	core/src/extensions/ai-engines/LocalOAIEngine.ts
#	extensions/monitoring-extension/src/node/index.ts
#	extensions/tensorrt-llm-extension/src/index.ts
#	extensions/tensorrt-llm-extension/src/node/index.ts
#	web/hooks/useSendChatMessage.ts

Signed-off-by: James <[email protected]>
Co-authored-by: James <[email protected]>

Chore: Add tinyllama back to model hub