Louis d85d02693b
feat: Nitro-Tensorrt-LLM Extension (#2280)
* feat: tensorrt-llm-extension

* fix: loading

* feat: add download tensorrt llm runner

Signed-off-by: James <james@jan.ai>

* feat: update to rollupjs instead of webpack for monitoring extension

Signed-off-by: James <james@jan.ai>

* feat: move update nvidia info to monitor extension

Signed-off-by: James <james@jan.ai>

* allow download tensorrt

Signed-off-by: James <james@jan.ai>

* update

Signed-off-by: James <james@jan.ai>

* allow download tensor rt based on gpu setting

Signed-off-by: James <james@jan.ai>

* update downloaded models

Signed-off-by: James <james@jan.ai>

* feat: add extension compatibility

* dynamic tensor rt engines

Signed-off-by: James <james@jan.ai>

* update models

Signed-off-by: James <james@jan.ai>

* chore: remove ts-ignore

* feat: getting installation state from extension

Signed-off-by: James <james@jan.ai>

* chore: adding type for decompress

Signed-off-by: James <james@jan.ai>

* feat: update according Louis's comment

Signed-off-by: James <james@jan.ai>

* feat: add progress for installing extension

Signed-off-by: James <james@jan.ai>

* chore: remove args from extension installation

* fix: model download does not work properly

* fix: do not allow user to stop tensorrtllm inference

* fix: extension installed style

* fix: download tensorrt does not update state

Signed-off-by: James <james@jan.ai>

* chore: replace int4 by fl16

* feat: modal for installing extension

Signed-off-by: James <james@jan.ai>

* fix: start download immediately after press install

Signed-off-by: James <james@jan.ai>

* fix: error switching between engines

* feat: rename inference provider to ai engine and refactor to core

* fix: missing ulid

* fix: core bundler

* feat: add cancel extension installing

Signed-off-by: James <james@jan.ai>

* remove mocking for mac

Signed-off-by: James <james@jan.ai>

* fix: show models only when extension is ready

* add tensorrt badge for model

Signed-off-by: James <james@jan.ai>

* fix: copy

* fix: add compatible check (#2342)

* fix: add compatible check

Signed-off-by: James <james@jan.ai>

* fix: copy

* fix: font

* fix: copy

* fix: broken monitoring extension

* chore: bump engine

* fix: copy

* fix: model copy

* fix: copy

* fix: model json

---------

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: Louis <louis@jan.ai>

* fix: vulkan support

* fix: installation button padding

* fix: empty script

* fix: remove hard code string

---------

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: NamH <NamNh0122@gmail.com>
2024-03-14 14:07:22 +07:00

74 lines
2.6 KiB
TypeScript

import resolve from '@rollup/plugin-node-resolve'
import commonjs from '@rollup/plugin-commonjs'
import sourceMaps from 'rollup-plugin-sourcemaps'
import typescript from 'rollup-plugin-typescript2'
import json from '@rollup/plugin-json'
import replace from '@rollup/plugin-replace'
const packageJson = require('./package.json')
export default [
{
input: `src/index.ts`,
output: [{ file: packageJson.main, format: 'es', sourcemap: true }],
watch: {
include: 'src/**',
},
plugins: [
replace({
EXTENSION_NAME: JSON.stringify(packageJson.name),
TENSORRT_VERSION: JSON.stringify('0.1.5'),
DOWNLOAD_RUNNER_URL:
process.platform === 'darwin' || process.platform === 'win32'
? JSON.stringify(
'https://github.com/janhq/nitro-tensorrt-llm/releases/download/windows-v<version>/nitro-windows-v<version>-amd64-tensorrt-llm-<gpuarch>.tar.gz'
)
: JSON.stringify(
'https://github.com/janhq/nitro-tensorrt-llm/releases/download/linux-v<version>/nitro-linux-v<version>-amd64-tensorrt-llm-<gpuarch>.tar.gz'
),
NODE: JSON.stringify(`${packageJson.name}/${packageJson.node}`),
INFERENCE_URL: JSON.stringify(
process.env.INFERENCE_URL ||
`${packageJson.config?.protocol ?? 'http'}://${packageJson.config?.host}:${packageJson.config?.port}/v1/chat/completions`
),
COMPATIBILITY: JSON.stringify(packageJson.compatibility),
}),
json(),
typescript({ useTsconfigDeclarationDir: true }),
commonjs(),
resolve({
extensions: ['.js', '.ts', '.svelte'],
}),
sourceMaps(),
],
},
{
input: `src/node/index.ts`,
output: [
{ file: 'dist/node/index.cjs.js', format: 'cjs', sourcemap: true },
],
external: ['@janhq/core/node'],
watch: {
include: 'src/node/**',
},
plugins: [
replace({
LOAD_MODEL_URL: JSON.stringify(
`${packageJson.config?.protocol ?? 'http'}://${packageJson.config?.host}:${packageJson.config?.port}/inferences/tensorrtllm/loadmodel`
),
TERMINATE_ENGINE_URL: JSON.stringify(
`${packageJson.config?.protocol ?? 'http'}://${packageJson.config?.host}:${packageJson.config?.port}/inferences/processmanager/destroy`
),
ENGINE_HOST: JSON.stringify(packageJson.config?.host ?? '127.0.0.1'),
ENGINE_PORT: JSON.stringify(packageJson.config?.port ?? '3928'),
}),
json(),
typescript({ useTsconfigDeclarationDir: true }),
commonjs(),
resolve({
extensions: ['.ts', '.js', '.json'],
}),
sourceMaps(),
],
},
]