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)
- [Feature]: Allow user defined extra request args to be logged in OpenAI compatible server HOT 3
- [Bug][v0.5.0]: Benign error reported by Python multiprocessing resource_tracker HOT 3
- [Bug]: Prefix Caching with Multi-Lora Support
- [Usage]: OpenRLHF: How can I create a second NCCL Group in a vLLM v0.4.3+ Ray worker? HOT 1
- [Bug]: Loading Mixtral-8x22B-Instruct-v0.1-FP8 on 8xL40S causes a SIGSEGV HOT 2
- [Usage]: Can I use vllm.LLM(quantization="bitsandbytes"...) when bitsandbytes is supported in the v0.5.0 version HOT 4
- [Bug]: NCCL hangs and causes timeout HOT 4
- [Bug]: Embedding model don't support distributed pooling
- [Bug]: Build from source but got unexpected symbol HOT 2
- [Bug]: ImportError: cannot import name 'boolean_dispatched' from partially initialized module 'torch._jit_internal' HOT 3
- [Feature]: 我们可以让vllm支持tensorrt编译之后的engine吗 HOT 1
- 当调用接口,不传system时,输出卡主了,输出全是!!!!! HOT 1
- [Feature]: load/unload API to run multiple LLMs in a single GPU instance
- [Usage]: How do I get the FP8 scaling factors for KV cache? HOT 3
- [Bug]: ray not work when tp>=2 HOT 8
- [Bug]: Qwen/Qwen2-72B-Instruct 128k server down HOT 2
- [Bug]: RuntimeError: out must have shape (total_q, num_heads, head_size_og) HOT 3
- [Bug]: ailed to import from vllm._C with ImportError('/usr/local/lib/python3.8/dist-packages/vllm/_C.abi3.so: undefined symbol: _ZN5torch7LibraryC1ENS0_4KindESsSt8optionalIN3c1011DispatchKeyEEPKcj') HOT 9
- [Usage]: RAG system HOT 8
- [Bug]: ModuleNotFoundError: No module named 'bitsandbytes' HOT 4
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.