Discover

Pulse Activity Analytics Best for Map Orgs

Niches

Agents MCP RAG Coding Assistants Inference & Serving Vector DBs

Personal

Watchlist Compare Weekly report

magic link · no password

LIVE──────── · ──:──:── UTCabout

Discover

Pulse Activity Analytics Best for Map Orgs

Niches

Agents MCP RAG Coding Assistants Inference & Serving Vector DBs

Personal

Watchlist Compare Weekly report

magic link · no password

Nicheinference

Inference & Serving

[TOOLS_TRACKED]36

[ACCELERATING]0

[DYING]0

[AVG_VELOCITY]0.47/10

See our pick → Best Inference & Serving

[ACCELERATING]

Accelerating

0

No accelerating tools right now.

[STABLE]

Stable

9

Tool

Trend 30d

Δ 7d

Class

vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
4.28↑ +84184kStable
ray-project/rayRay is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
2.30↑ +8243kStable
google-ai-edge/mediapipeCross-platform, customizable ML solutions for live and streaming media.
2.22↑ +9736kStable
jd-opensource/xllmA high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.
1.46↑ +181.4kStable
OpenRLHF/OpenRLHFAn Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
0.85↑ +279.7kStable
Avarok-Cybersecurity/atlasPure Rust Inference Engine
0.78↑ +18529Stable
xorbitsai/inferenceSwap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
0.77↑ +199.4kStable
GeeeekExplorer/nano-vllmNano vLLM
0.53↑ +8114kStable
bentoml/BentoMLThe easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
0.52↑ +98.7kStable

LIVE──────── · ──:──:── UTCabout