Comments (4)
Thanks for your advice. We are testing fp16 correctness and speed internally and will make it public soon
from web-llm.
Thanks for your advice. We are testing fp16 correctness and speed internally and will make it public soon
I'm wondering about what the web demo uses currently. The model size is similar to a q4_0 ggml model, so is it running 4bit? I couldn't find any specific info on what precision you guys are using.
from web-llm.
it is using 4bit quantization and fp32 for compute
from web-llm.
it is using 4bit quantization and fp32 for compute
Thank you. Good luck with everything, I'm looking forward to seeing how this progresses.
from web-llm.
Related Issues (20)
- Link in main readme doesn't work HOT 1
- Error running the function calling example: Cannot find global function mlc.serve.BNFGrammarGetGrammarOfJSON HOT 3
- BufferSource argument is empty HOT 4
- [MLC-LLM] Uncaught (in promise) LinkError: WebAssembly.instantiate(): Import #4 "env" HOT 2
- IndexedDB cache fails like the caches HOT 6
- Create a simpler web-workers example HOT 2
- Error: Cannot find global function tvmjs.runtime.ArrayConcat HOT 3
- next-simple chat - ReferenceError: require is not defined in ES module scope, you can use import instead HOT 10
- Do you plan to support LLaVA or video-LLaVA?
- Check failed: (!free_page_ids_.empty()) is false: The KV cache is full. No page can be allocated.
- Models output is scrambled in Safari Technology Preview, which has WebGPU support HOT 1
- Generate error, OperationError: Device lost during onSubmittedWorkDone (do not use this error for recovery - it is NOT guaranteed to happen on device loss) HOT 2
- Strange reply from Phi2-q4f32_1-1k model in running the Web-llm Chat Demo
- Cache.add() encountered a network error HOT 6
- Create a chat webapp with elegant UI on mlc.ai HOT 5
- Cannot find WebGPU on Safari (works on Arc) HOT 2
- Fetching model param super slow on Vercel HOT 1
- Engine not instantiating for WebWorker
- In the Llama-2-7b-chat-hf-q4f32_1-1k model, the number of tokens in the prefill is 36 when inputting 'hello'. HOT 2
- [Tracking] WebLLM: Frontend Compatibility Issues and CDN Delivery HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from web-llm.