Comments (1)
depenglee1707
commented on June 11, 2024
Just for the speed of inference, I guess sglang will be better, since it direct adopt RadixAttention and the same thing still in our roadmap.
Our project is more focus on deploying models in production level, since we introduced the scale, serverless and model deployment template .etc and other ops things to help people maintain the inferences easier.
from llm-inference.
Related Issues (20)
- Model streaming API enhancement HOT 2
- Support load Qwen1.5-72B-Chat-GPTQ-Int4 by auto_gptq HOT 1
- Failed to load qwen1_5-72b-chat-q5_k_m.gguf HOT 3
- vllm cannot address "runtime_env" HOT 1
- support "revision" in yaml defination HOT 2
- API server startup slow HOT 1
- Model inference cross multi-nodes
- Requested tokens (817) exceed context window of 512 HOT 3
- The usage introduction of `llm-serve` is not correct in quick_start.md
- Add inference SDK for invoke
- enable reset generate config on fly
- vllm, gguf, llamacpp, these integration cannot address local path of model
- avoid to ping huggingface when start serving to speed up the deployement
- vllm implements cannot support download model from repo besides hg HOT 2
- GGUF implements will make duplicate copy since cannot detect config.json file in the cache folder
- Error happen when do inference for wukong dtype=bfloat16 of use default transformer pipeline load model HOT 1
- Upgrade ray 2.20.0 HOT 1
- Auto load models from ./models for when api server start HOT 1
- Api server was blocked when LLM deployment scaling config beyond the cluster resouces
- Api server blocked when one request is in-process HOT 1
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 llm-inference.