Comments (1)
I have started looking at this issue. I will be basing my implementation on this reference implementation in medusa (https://sourcegraph.com/github.com/FasterDecoding/Medusa@e2a5d20c048a9b0a4092e6933c34313687422518/-/blob/medusa/model/utils.py?L404)
from vllm.
Related Issues (20)
- [Usage]: No chat template provided. Chat API will not work. How do I get vllm to support Codellama-34B in openai format?
- [Installation]: Problem with docker image (ROCm version)
- [Usage]: How can I expand the block size?
- (not planned)
- [Bug]: vLLM server crashes when getting logprobs of prompt HOT 1
- [Usage]: How to sample multiple times?
- [Bug]: inter-token latency is lower than TPOT in serving benchmark result HOT 1
- [Bug]: HOT 1
- [Bug]: vllm not support fp8 kv cache when use flashinfer
- [Bug]: vllm turned off my pc (loading mixtral8x7b) HOT 1
- who can help me install vllm (at least 0.4.2) in mi50 8-gpus machine. [Installation]:
- [Feature]: return Usage info for streaming request for each chunk in ChatCompletion
- [Usage]: How to release GPU of vLLM model in python code HOT 2
- [Feature]: mistralai/Mistral-Nemo-Instruct-2407 support HOT 4
- [Usage]: How to invoke all the tests in vLLM HOT 2
- [Bug]: vllm doesn't support multi-instance GPU HOT 10
- [RFC]: Single Program Multiple Data (SPMD) Worker Control Plane HOT 1
- [Bug]: Cannot load fp8 model of internlm2-chat-7b offline HOT 2
- [Performance]: GPU utilization is low when running large batches on H100 HOT 1
- [Usage]: Can't utilize all VRAM for context
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 vllm.