Repositories
33
Net stars gained, last 7 days
+9,486
Top-level Tag
Net stars gained each day, last 90 days
Peak days
- 1
Oct 3, 2026 +2,515 net stars (median day +725)
- Niko1221/Strata+1,928 (77%)
Created on Sep 24, 2026
- antirez/ds4+208 (8%)
- ggml-org/llama.cpp+83 (3%)
- 2
Oct 4, 2026 +3,527 net stars (median day +725)
- Niko1221/Strata+2,883 (82%)
Created on Sep 24, 2026
- antirez/ds4+279 (8%)
- ggml-org/llama.cpp+87 (2%)
- 3
Oct 5, 2026 +3,091 net stars (median day +725)
- Niko1221/Strata+2,624 (85%)
Created on Sep 24, 2026
- ggml-org/llama.cpp+115 (4%)
- antirez/ds4+93 (3%)
- 4
Oct 20, 2026 +3,003 net stars (median day +725)
- Niko1221/Strata+871 (29%)
- eagle-hq/EAGLE-4+454 (15%)
Published v0.1.0 on Oct 20, 2026 · Created on Oct 20, 2026
- vllm-project/vllm+394 (13%)
- 5
Oct 21, 2026 +2,815 net stars (median day +725)
- Niko1221/Strata+685 (24%)
Published v0.2.2 on Oct 21, 2026
- vllm-project/vllm+458 (16%)
- NVIDIA/spark-local-inference+343 (12%)
Created on Oct 20, 2026
A peak day has at least 2 times the net stars of the median day of this chart, and at least 100 more. For each peak day, the list shows the repositories that gained the most net stars that day. It also shows their GitHub releases of that day or the day before (UTC), and their creation date when it was 14 days or less before. These events occur near the same day. They do not show why the stars came.
Largest
Most stars in total now.
readme:
llama-server REST API
description:
A high-throughput and memory-efficient inference and serving engine for LLMs
readme:
Drop-in API compatibility**: OpenAI, Anthropic, and ElevenLabs APIs across every backend
readme:
exo connects all your devices into an AI cluster.
readme:
A distributed multi-model serving system with web UI and OpenAI-compatible RESTful APIs.
description:
Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
description:
SGLang is a high-performance serving framework for large language models and multimodal models.
readme:
MAX inference server: /max/python/max/serve (OpenAI-compatible endpoint, since May 2025)
- antirez/ds424K
readme:
You can use multiple CUDA cards as a multi-user LLM server.
readme:
MLCEngine provides OpenAI-compatible API available through REST server, python, javascript, iOS, Android, all backed by the same engine and compiler that we keep improving with the community.
Newest Admissions
Entered the index by the rising rule, newest first.
description:
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API
readme:
Developers can connect their own apps through its Ollama-, OpenAI- and Anthropic-compatible APIs or its Swift library.
readme:
The built-in native server exposes one Engine through OpenAI Chat Completions and Responses, Anthropic Messages, and a small demo chat page.
- thu-nics/AKV171
readme:
an SGLang-based inference system that executes those operations while reusing compatible KV cache
readme:
A large MoE model runs on one workstation, behind an OpenAI- and Anthropic-compatible API.
readme:
ModelSphere is an open-source LLM inference platform designed to make production-grade model serving simple, efficient, and continuously optimized.
- eagle-hq/EAGLE-41.1K
readme:
EAGLE-4 (Extrapolation Algorithm for Greater Language-model Efficiency) speeds up LLM inference with speculative decoding.
readme:
Flare is a local inference server for NVIDIA SM120/SM121 GPUs, built for long conversations, coding agents, and repeated tool use.
readme:
Serve **DeepSeek-V4.1-Flash-1017** from two NVIDIA DGX Sparks (GB10, 128 GB each, linked by their ConnectX-7 ports)
readme:
Kapitsa is an inference engine for Apple silicon that runs Qwen, Nemotron and Recursive's Flint models locally, built for coding agents.
How a repository gets this Tag
An agent reads the description, the GitHub topics, and the start of the README of each repository. It chooses Tags only from the Tag list in the AwesomeRepos source code. For each Tag, it quotes the text. A code check keeps the Tag only when the quote is in that text. The quote under each repository is that evidence. A Tag does not rank repositories. It does not say that one repository can replace another. To report a wrong Tag, use "Report a problem with this page" on the page of the repository. All numbers on this page count only visible repositories.