Ghostlink

Distributed LLM inference fabric for heterogeneous local clusters. Features zero-copy SPSC ring buffers, automated tuning, and an OpenAI-compatible API.

rwilliamspbg-ops/Ghostlink

View on GitHub ↗

Distributed LLM inference fabric for heterogeneous local clusters. Features zero-copy SPSC ring buffers, automated tuning, and an OpenAI-compatible API.

Ghostlink grew +1.2% in the last 30 days, ranks 88th of 99 in Distributed Inference, actively maintained, last commit 5 days ago.

Star trajectory

42 days tracked
2026-10-1185 stars today2026-11-22
Momentum

+1.2% in 30d, below the Distributed Inference median of +1.2%.

Maintenance

Last commit 5 days ago, staler than the median of 5d.

How it compares in Distributed Inference

Ghostlink
85
stars
+1.2% 30d
commit 5 days ago
Distributed Inference median
299
stars
+1.2% 30d
commit ~5d ago
Leader · exo
48.5k
stars
+1.1% 30d
commit 15 days ago

Ranked 88th of 99 by stars.

Ranked by shared tags, then keywords, then stars
  1. 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, Distributed Inference, Local Runtime / Inference Engine

  2. Kindi 0.6.1: fast local LLM inference on low-cost GPUs and CPUs. DeepSeek-V4.1-Flash (552B) at 18.7 tok/s on…

    Committed 5d ago · Python · AGPL-3.0

    Shares Local Runtime / Inference Engine, Production Serving & Deployment, Distributed Inference

  3. Aggregates compute from spare GPU capacity

    +2 (+0.9%) in 30d · Committed 3d ago · TypeScript · Apache-2.0

    Shares Distributed Inference, Local Runtime / Inference Engine, Production Serving & Deployment

  4. GPU environment and cluster management with LLM support

    +2 (+0.3%) in 30d · Committed 919d ago · Python · AGPL-3.0

    Shares Local Runtime / Inference Engine, Distributed Inference, Production Serving & Deployment

  5. Universal Python SDK to run AI workloads on Kubernetes

    +7 (+4.5%) in 30d · Committed today · Python · Apache-2.0

    Shares Distributed Inference, Local Runtime / Inference Engine, Production Serving & Deployment

  6. Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM…

    +71 (+11%) in 30d · Committed today · Rust · Apache-2.0

    Shares Production Serving & Deployment, Distributed Inference

  7. llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

    +2 (+0.7%) in 30d · Committed 2d ago · Go · MIT

    Shares Local Runtime / Inference Engine, Production Serving & Deployment

  8. Hybrid GPU + CPU inference for mixture-of-experts models, written in Rust down to the CUDA kernels. A drop-in…

    Committed today · Rust · MIT

    Shares Local Runtime / Inference Engine, Production Serving & Deployment

  9. Open-source infrastructure for the full inference lifecycle: deploy, observe, scale, optimize, and safely…

    -22 (-41%) in 30d · Committed today · Go · Apache-2.0

    Shares Production Serving & Deployment, Distributed Inference

  10. A Rust-native LLM serving engine. One binary, no Python runtime.

    +1 (+4.8%) in 30d · Committed today · Rust · MIT

    Shares Local Runtime / Inference Engine, Production Serving & Deployment

Language
Rust
License
MIT License
Contributors
11
Forks
11
Watchers
3
Open issues
0
Releases
18
Created
2026-06-19
Stars this week
+0

You've seen where Ghostlink stands today.

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

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

Maintain Ghostlink?

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

Claim this page