RedKnot

Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention

rednote-machine-learning/RedKnot

View on GitHub ↗

Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention

RedKnot grew +12.8% in the last 30 days, ranks 14th of 343 in Inference Optimization, actively maintained, last commit 3 days ago.

Star trajectory

82 days tracked
2026-08-313k stars today2026-11-22
Momentum

+12.8% in 30d, above the Inference Optimization median of +1.6%.

Maintenance

Last commit 3 days ago, fresher than the median of 16d.

How it compares in Inference Optimization

RedKnot
3k
stars
+12.8% 30d
commit 3 days ago
Inference Optimization median
242
stars
+1.6% 30d
commit ~16d ago
Leader · supertonic
13.8k
stars
-0.1% 30d
commit 74 days ago

Ranked 14th of 343 by stars.

Ranked by shared tags, then keywords, then stars

Where RedKnot sits

Hover or focus a node for details. Click to open it.

  • This repo
  • Related repo
  • Tag or category
  1. Lucebox inference engine for heterogeneous hardware & consumer GPUs

    +76 (+2.6%) in 30d · Committed today · C++ · Apache-2.0

    Shares Inference Optimization, Production Serving & Deployment

  2. A high-performance inference engine for LLM, VLM and DiT models, optimized for diverse AI accelerators. It is…

    +23 (+1.4%) in 30d · Committed today · C++ · Apache-2.0

    Shares Inference Optimization, Production Serving & Deployment

  3. Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4…

    +962 (+243%) in 30d · Committed 3d ago · C++ · MIT

    Shares Inference Optimization, Production Serving & Deployment

  4. Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

    Committed today · C++ · Apache-2.0

    Shares Inference Optimization, Production Serving & Deployment

  5. Official Inference Code of EAGLE-4

    +334 (+38%) in 30d · Committed 8d ago · Python · Other license

    Shares Inference Optimization, Production Serving & Deployment

  6. TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

    +21 (+1.8%) in 30d · Committed 55d ago · C++ · MIT

    Shares Inference Optimization, Production Serving & Deployment

  7. Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

    +25 (+3.5%) in 30d · Committed yesterday · Rust · Apache-2.0

    Shares Production Serving & Deployment, Inference Optimization

  8. Run many AI agents at once on your Mac, up to 3x faster.

    +273 (+91%) in 30d · Committed today · Python · Apache-2.0

    Shares Production Serving & Deployment, Inference Optimization

  9. Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit…

    Committed 26d ago · Python

    Shares Production Serving & Deployment, Inference Optimization

  10. Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM)…

    +264 (+90%) in 30d · Committed today · C++ · MIT

    Shares Production Serving & Deployment, Inference Optimization

Language
Python
License
Apache License 2.0
Contributors
5
Forks
1.7k
Watchers
103
Open issues
7
Releases
0
Created
2026-06-04
Stars this week
-162

You've seen where RedKnot stands today.

Get the moves before everyone else: the 5 Inference Optimization repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain RedKnot?

Claim this page to add your own call-to-action.

Claim this page