Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Open Source Continuous Inference Benchmark Research Platform — Kimi K3 2.8T, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3 | 开源持续推理基准研究平台 — Kimi K2.7-Code、MiniMax M3、DeepSeekv4、GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72，即将推出™ TPUv6e/v7/Trainium2/3
| Date | Stars |
|---|---|
| 2026-07-24 | 1278 |
| 2026-07-25 | 1280 |
| 2026-07-28 | 1291 |
| 2026-07-30 | 1291 |
| 2026-08-06 | 1291 |
| 2026-08-07 | 1332 |
| 2026-08-15 | 1385 |
| 2026-08-18 | 1399 |
| 2026-08-19 | 1409 |
| 2026-08-20 | 1414 |
| 2026-08-21 | 1417 |
| 2026-08-22 | 1422 |
| 2026-08-23 | 1425 |
| 2026-08-24 | 1469 |
| 2026-08-25 | 1521 |
| 2026-08-26 | 1549 |
| 2026-08-27 | 1568 |
| 2026-08-28 | 1573 |
| 2026-08-29 | 1580 |
| 2026-08-30 | 1585 |
| 2026-08-31 | 1593 |
| 2026-09-01 | 1603 |
| 2026-09-02 | 1613 |
| 2026-09-03 | 1614 |
| 2026-09-04 | 1622 |
| 2026-09-05 | 1627 |
| 2026-09-06 | 1629 |
| 2026-09-07 | 1631 |
| 2026-09-08 | 1635 |
| 2026-09-09 | 1645 |
| 2026-09-10 | 1660 |
| 2026-09-11 | 1667 |
| 2026-09-12 | 1669 |
| 2026-09-13 | 1670 |
| 2026-09-14 | 1675 |
| 2026-09-15 | 1695 |
| 2026-09-16 | 1706 |
| 2026-09-17 | 1716 |
| 2026-09-18 | 1722 |
| 2026-09-19 | 1732 |
| 2026-09-20 | 1740 |
Today
+8 stars today
This week
+70 stars this week
This month
+323 stars this month
Momentum
102.0
growth rate 4.19%/day
# InferenceX™, Open Source Continuous Inference Standard and Research Platform / 开源持续推理标准与研究平台 <p align="center"> <a href="https://github.com/SemiAnalysisAI/InferenceX/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/badge/License-Apache%202.0-blue.svg"></a> <a href="https://github.com/SemiAnalysisAI/InferenceX/pulls"><img alt="PRs Welcome" src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg"></a> <a href="https://inferencex.semianalysis.com/"><img alt="Dashboard" src="https://img.shields.io/badge/Performance-Dashboard-blue"></a> <a href="https://deepwiki.com/SemiAnalysisAI/InferenceX"><img alt="Ask DeepWiki" src="https://deepwiki.com/badge.svg"></a> <a href="https://github.com/SemiAnalysisAI/InferenceX"><img alt="GitHub Stars" src="https://img.shields.io/github/stars/SemiAnalysisAI/InferenceX?style=social"></a> </p> <div align="center"> **English** | [中文](./README_zh.md) </div> Trusted by Operators of Trillion Dollar Token Factories such as OpenAI, Meta, Microsoft, Oracle, etc, & ML Community such as PyTorch Foundation, vLLM, SGLang, Tri Dao ## News - **[2026/09]** DeepSeek V4.1 Flash: added AgentX benchmarks [dashboard](https://inferencex.semianalysis.com/agentx) - **[2026/08]** Qwen3.8-Flash-Next: added AgentX benchmarks with native multi-token prediction (MTP) [dashboard](https://inferencex.semianalysis.com/agentx) - **[2026/08]** 🔥 **AgentX: World's First Fully Open Source Apache 2.0 Realistic 1Mil+ Long Context, Multi Turn Benchmark Live** [dashboard](https://inferencex.semianalysis.com/agentx) - **[2026/08]** 🔥 GLM5.3: continuous agentic benchmarks live too [dashboard](https://inferencex.semianalysis.com/) - **[2026/07]** 🔥 Kimi K3 2.8T: continuous benchmarks live since Day 0 - **[2026/06]** 🔥 MiniMax M3: continuous benchmarks live since Day 0 [dashboard](https://inferencex.semianalysis.com/inference?preset=minimax-m3-launch) - **[2026/04]** 🔥 DeepSeek V4 Pro 1.6T: continuous benchmarks live since Day 0 [article](https://newsletter.semianalysis.com/p/deepseekv4-16t-day-0-to-day-43-performance), [dashboard](https://inferencex.semianalysis.com/inference?preset=dsv4-launch) - **[2026/03]** 🔥 Qwen3.5 397B: continuous benchmarks live since Day 0 [dashboard](https://inferencex.semianalysis.com/) - **[2026/03]** Added Kimi K2.5 (same architecture as Kimi 2.7-Code), GLM5 (same arch as GLM5.1), and MiniMax M2.5 (same arch as MiniMax M2.7) [dashboard](https://inferencex.semianalysis.com/) - **[2026/02]** GB300 NVL72: added to InferenceX & continuously benchmarked [SGLang Maintainer Lmsys Blog](https://www.lmsys.org/blog/2026-02-20-gb300-inferencex/) - **[2026/02]** 🔥 InferenceX v2 launch comparing NVIDIA Blackwell, AMD, and Hopper [article](https://newsletter.semianalysis.com/p/inferencex-v2-nvidia-blackwell-vs) - **[2025/10]** 🔥 InferenceX (formerly InferenceMAX) v1 launch [article](https://newsletter.semianalysis.com/p/inferencemax-open-source-inference) ## Introduction InferenceX™ (formerly InferenceMAX) is an inference performance research platform dedicated to continually analyzing & benchmarking the world’s most popular open-source inference frameworks used by major token factories and models to track real performance in real time. As these software stacks improve, InferenceX™ captures that progress in near real-time, providing a live indicator of inference performance progress. A [open sourced](https://github.com/SemiAnalysisAI/InferenceX-app) live dashboard is available for free publicly at https://inferencex.com/. > [!IMPORTANT] > Only [SemiAnalysisAI/InferenceX](https://github.com/SemiAnalysisAI/InferenceX) repo contains the Official InferenceX™ result, all other forks & repos are Unofficial. The benchmark setup & quality of machines/clouds in unofficial repos may be differ leading to subpar benchmarking. Unofficial must be explicitly labelled as Unofficial. > Forks may not remove this disclaimer <img width="2544" height="1424" alt="InferenceX DeepSeekv4 MXFP4 Per
Excerpt of 7,237 characters
Read on GitHub
423
functionstackx
393
272
187
72
64
47
40
29
25
23
20
19
18
17
17
16
15
14
13
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:71e2c46de2b0b183, topic:vllm
matched fp:71e2c46de2b0b183, topic:cuda
matched fp:71e2c46de2b0b183, topic:pytorch
matched fp:71e2c46de2b0b183, topic:llm