EAGLE-4 speculative decoding goes open source with SGLang and vLLM plugins
testingcatalog · x · 2026-10-21
EAGLE-4 is now open source on GitHub as eagleharness, serving speculative-decoding drafts to SGLang, vLLM, and TokenSpeed via engine plugins. The project is positioned as "one flexible drafter for all batch sizes and hardware."
- The repo ships official inference code, docs, tests, and the EAGLE-4 paper PDF, plus a commercial license agreement
- An EAGLE-4 draft model for Qwen3 27B is available on HuggingFace alongside the research paper
- A testing link is provided to try the speedup directly
Related event: EAGLE-4 Open-Source Speculative Decoding Hits 961.6 Tokens/s(2 posts)→
More from Infra
- ai& claims to be Japan's biggest dedicated inference platform with 100MW+ data centers — DavidBennett__ · 2026-10-21
- SpaceX Reportedly Adding 10GW of Compute by 2027, Up from 1.7GW Today — beffjezos · 2026-10-21
- Musk's Hunt for Rentable GPU Compute Turns Into a Real-Life Cheese Shop Sketch — XFreeze · 2026-10-21
- Cloudflare discloses compromised eMudhra intermediate certificates, urges patching — Cloudflare Blog · 2026-10-21
- Shotwell: Starlink now contracted for ~12,000 planes, a quarter of available aircraft — XFreeze · 2026-10-21
- Samsung Electro-Mechanics signs $260M substrate deal with Micron as AI shortage spreads down the stack — demian_ai · 2026-10-21