Simon Mo

[Model] DeepSeek-V3 Enhancements

43

This issue tracks follow up enhancements after initial support for the Deepseek V3 model. Please feel free to chime in and contribute! - [x] Follow up #11523: enhance testing with...

Loading models from an S3 location instead of local path

7

### Discussed in https://github.com/vllm-project/vllm/discussions/3072 Originally posted by **petrosbaltzis** February 28, 2024 Hello, The VLLM library gives the ability to load the model and the tokenizer either from a local folder...

[RFC]: Drop Support for OpenVINO

1

### Motivation. OpenVINO backend was initially integrated as an alternatively to the CPU backend and has branched out the vLLM execution logic for every levels (executor, model runner, and attention...

[Roadmap] vLLM Roadmap Q2 2025

3

This page is accessible via [roadmap.vllm.ai](https://roadmap.vllm.ai/) This is a living document! For each item here, we intend to link the RFC as well as discussion Slack channel in the [vLLM...

[Usage] Qwen3 Usage Guide

82

vLLM v0.8.4 and higher natively supports all Qwen3 and Qwen3MoE models. Example command: * `vllm serve Qwen/... --enable-reasoning --reasoning-parser deepseek_r1` * All models should work with the command as above....

[Feature]: Simple Data Parallelism in vLLM

15

### 🚀 The feature, motivation and pitch It is common to have a scenario where folks want to deploy multiple vLLM instances on a single machine due to the machine...

[Roadmap] vLLM Roadmap Q4 2025

10

This page is accessible via [roadmap.vllm.ai](http://roadmap.vllm.ai/) This is a living document! For each item here, we intend to link the RFC as well as discussion Slack channel in the [vLLM...