Back: Catalog

pd-bridge

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

PD

pd-bridge

New65

chadhurley25075-png · AI / LLM / RAG

STARS151
FORKS13
COMMITS0
CONTRIBUTORS0
VERSION—
UPDATED14 days ago
apple-silicondeepseekdgx-sparkheterogeneous-inferenceApache-2.0

Common commercial products in this category: ChatGPT, Claude, Gemini

What can it do?
  • The fallback works, and it can no longer lie. When a bridge fails the reply still comes back
  • The "cold-start variance" at 20K was not variance. The 25.5 s vs 55.4 s spread was the capture
Heads up
  • • No published release
Website GitHub

My note

Alternative pages

ChatGPT alternativesClaude alternativesGemini alternatives

More in: AI / LLM / RAG