pd-bridge

Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE

chadhurley25075-png/pd-bridge

View on GitHub ↗

Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE

pd-bridge grew +0.7% in the last 30 days, ranks 78th of 99 in Distributed Inference, last commit 36 days ago.

Star trajectory

71 days tracked
2026-09-11151 stars today2026-11-22
Momentum

+0.7% in 30d, below the Distributed Inference median of +1.2%.

Maintenance

Last commit 36 days ago, staler than the median of 5d.

How it compares in Distributed Inference

pd-bridge
151
stars
+0.7% 30d
commit 36 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 78th of 99 by stars.

Ranked by shared tags, then keywords, then stars
  1. Peer-to-peer LLM inference in the browser: pool your devices to run big open models, for chat and coding…

    +56 (+9.3%) in 30d · Committed 19d ago · JavaScript · MIT

    Shares Web / Edge / On-Device Runtime, Distributed Inference, Inference Optimization

  2. Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully…

    +8 (+7.1%) in 30d · Committed 114d ago · C

    Shares Web / Edge / On-Device Runtime, Distributed Inference, Inference Optimization

  3. [Official] Prima.cpp: Scale Your Local AI Beyond One Device.

    +20 (+18%) in 30d · Committed 76d ago · C++ · MIT

    Shares Distributed Inference, Web / Edge / On-Device Runtime, Inference Optimization

  4. Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

    +442 (+6.3%) in 30d · Committed 7d ago · Swift · Apache-2.0

    Shares Web / Edge / On-Device Runtime, Inference Optimization

  5. The fastest way to run Inkling 2 Mini, Qwen 3.8 and Ternary Bonsai 2 27B on a Mac: Inkling 2 Mini at up to…

    +107 (+4.1%) in 30d · Committed today · Python · Apache-2.0

    Shares Inference Optimization, Web / Edge / On-Device Runtime

  6. 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 Inference Optimization, Distributed Inference

  7. A high-performance inference system for large language models, designed for production environments.

    -1 (-0.2%) in 30d · Committed 338d ago · C++ · Apache-2.0

    Shares Inference Optimization, Distributed Inference

  8. 🧱 Experimental library for building inference engines

    Committed today · Python · Apache-2.0

    Shares Inference Optimization, Distributed Inference

  9. OrbitKV is a High Performance KV Cache System for LLM Inference.

    -52 (-15%) in 30d · Committed yesterday · Rust · Apache-2.0

    Shares Inference Optimization, Web / Edge / On-Device Runtime

  10. CacheRoute is an innovative LLM scheduling scheme dedicated to enabling flexible KV cache reuse across LLM…

    +41 (+17%) in 30d · Committed 103d ago · Python · Apache-2.0

    Shares Inference Optimization, Distributed Inference

Language
Python
License
Apache License 2.0
Contributors
4
Forks
13
Watchers
0
Open issues
1
Releases
0
Created
2026-09-06
Stars this week
+0

You've seen where pd-bridge 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 pd-bridge?

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

Claim this page