Spaces:

---

Xenova

/

experimental-phi3-webgpu

like 271

Running

(1) C:\Users\TARGET STORE\Desktop\1>cd onnxruntime-inference-examples\js\chat

(1) C:\Users\TARGET STORE\Desktop\1\onnxruntime-inference-examples\js\chat>npm run dev

[email protected] dev
webpack serve --no-client-overlay

[webpack-dev-server] Project is running at:
[webpack-dev-server] Loopback: http://localhost:8080/, http://[::1]:8080/
[webpack-dev-server] On Your Network (IPv4): http://192.168.1.2:8080/
[webpack-dev-server] On Your Network (IPv6): http://[fdd8:2918:e9a6:8000:e21b:8199:d8a3:f14e]:8080/
[webpack-dev-server] Content not from webpack is served from 'C:\Users\TARGET STORE\Desktop\1\onnxruntime-inference-examples\js\chat' directory
assets by path dist/.wasm 37.3 MiB
asset dist/ort-wasm-simd-threaded.jsep.wasm 19.7 MiB [emitted] [from: node_modules/onnxruntime-web/dist/ort-wasm-simd-threaded.jsep.wasm] [copied]
asset dist/ort-wasm-simd.jsep.wasm 17.6 MiB [emitted] [from: node_modules/onnxruntime-web/dist/ort-wasm-simd.jsep.wasm] [copied]
assets by path dist/.js 5.01 MiB
asset dist/main.min.js 2.5 MiB [emitted] [javascript module] (name: dist/main.min) 1 related asset
asset dist/main.js 2.5 MiB [emitted] [javascript module] (name: dist/main) 1 related asset
runtime modules 22.4 KiB 14 modules
modules by path ./node_modules/ 2.31 MiB
modules by path ./node_modules/@xenova/transformers/ 1.34 MiB 17 modules
modules by path ./node_modules/onnxruntime-common/dist/lib/.js 35.3 KiB 10 modules
modules by path ./node_modules/webpack-dev-server/client/ 84.8 KiB 8 modules
modules by path ./node_modules/webpack/hot/.js 5.17 KiB 4 modules

index.js:595 [webpack-dev-server] Server started: Hot Module Replacement enabled, Live Reloading enabled, Progress disabled, Overlay enabled.
log.js:39 [HMR] Waiting for update signal from WDS...
main.js:23 Your GPU or Browser does not support webgpu with fp16, using fp32 instead.
main.js:23 Loading model...
llm.js:8 loading... phi3, webgpu
llm.js:8 https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-onnx-web/resolve/main/config.json (cached)
llm.js:8 https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-onnx-web/resolve/main/onnx/model_q4.onnx (cached)
llm.js:8 https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-onnx-web/resolve/main/onnx/model_q4.onnx_data (cached)
llm.js:8 model size 2597 MB
main.js:23 Error: no available backend found. ERR: [webgpu] TypeError: r.requestAdapterInfo is not a function
at On (ort.webgpu.min.js:6:1623)
at async e.create (ort.webgpu.min.js:6:18113)
at async LLM.load (llm.js:113:1)
at async Init (main.js:256:1)
main.js:141 TypeError: Cannot read properties of undefined (reading 'run')
at LLM.generate (llm.js:209:1)
at Query (main.js:233:1)