vLLM

@vllm_project

A high-throughput and memory-efficient inference and serving engine for LLMs. Join slack.vllm.ai to discuss together with the community!

vllm.ai

Joined March 2024

Following

48.4K

Followers

Replies Reposts Media Articles

vLLM
@vllm_project
13h
🎉 Congrats to @AntLingAGI on open-sourcing Ling-3.0-flash-Fin and FinFIRST! Open models and expert-built benchmarks are a great step toward more accessible and verifiable financial AI. Looking forward to seeing these workflows run at scale with vLLM. 🚀
Ant Ling
@AntLingAGI
22h
We’re open-sourcing Ling-3.0-flash-Fin, a finance-enhanced model for real-world workflows, and FinFIRST, an expert-built benchmark for financial search agents. Two open releases, one goal: making financial AI more accessible and verifiable.
1
vLLM
@vllm_project
13h
Love seeing @lightseekorg use TorchSpec + vLLM to train three different K3 draft models, with the recipes open sourced too. Exactly the kind of training-serving collaboration we love to see 🚀
LightSeek Foundation
@lightseekorg
22h
Releasing the @Kimi_Moonshot K3 Draft Collection — 3 draft models (EAGLE-3, DFlash2, DSpark) trained with TorchSpec and @vllm_project on @NVIDIAAI GB200. 🚀 We also shared the data recipes. More on the blog → lightseek.org/blog/kimi-k3-d…
1
vLLM
@vllm_project
17h
Thank you to the @SemiAnalysis_ team for the shoutout and for the collaboration on AgentX 🙏 Benchmarks are only useful when they measure the workloads people actually run, and AgentX measures the real thing: multi-turn, long-context agent traffic. vLLM is the engine for
SemiAnalysis
@SemiAnalysis_
18h
Shoutout to the cracked team at @vllm_project that implemented recent agentic workload optimizations. (1/5)🧵
1
vLLM
@vllm_project
23h
K2-Horizon has day-0 support in vLLM, and IFM released intermediate checkpoints, detailed data-construction recipes, the training code, and fine-grained logs alongside the weights. 📷 512K context and Apache-2.0 from 3.7B up, with reasoning and tool calling in the checkpoints
Institute of Foundation Models
@IFM_AI
Sep 3
Introducing K2 Horizon: a connected fleet of six foundation models ranging from 0.9 billion to 375 billion parameters. - Frontier performance: Across coding and agentic tasks, K2 Horizon delivers top-tier performance in every size class—with the 0.9B, 3.7B and 7B models setting
3
vLLM
@vllm_project
Sep 1
🎬Video generation faster than playback! 🚀MiniMax H3 on vLLM-Omni + FastVideo's FastH3: a complete 10.1s MP4 - video AND synchronized audio - rendered in 8.7s!⚡️ Thanks to @MiniMax_AI for the great Minimax H3 release, the FastVideo team @haoailab for open-sourcing FastH3 and
22