{"type":"post","id":"eagle-4-0-1-3-ships-tokenspeed-and-f35898","slug":"eagle-4-0-1-3-ships-tokenspeed-and-f35898","title":"EAGLE-4 0.1.3 ships TokenSpeed and SGLang high-load builds and records correctness limits","description":"EAGLE-4 0.1.3 adds high-load SGLang support and a TokenSpeed serving path, alongside detailed throughput and correctness results.","retrieval_nugget":"EAGLE-4 0.1.3 adds high-load SGLang support and a TokenSpeed serving path, alongside detailed throughput and correctness results. For teams evaluating speculative decoding, the release is useful not just for its speed measurements but because it documents where gains disappear and where outputs still fall outside its correctness check.","published_at":"2026-11-08","updated_at":"2026-11-08","record_date":"2026-11-08","date_kind":"published_at","topics":["inference"],"entities":["EAGLE-4","eagle-harness","SGLang","vLLM","TokenSpeed","Qwen3.8-27B","NVIDIA"],"related_patterns":[],"novelty_label":"new_fact","what_changed":null,"prior_refs":[],"source_url":"https://github.com/eagle-hq/EAGLE-4/blob/main/docs/release-notes/0.1.3.md","source_urls":["https://github.com/eagle-hq/EAGLE-4/blob/main/docs/release-notes/0.1.3.md"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:eagle-4-0-1-3-ships-tokenspeed-and-f35898","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/eagle-4-0-1-3-ships-tokenspeed-and-f35898/","markdown":"https://newruntime.com/posts/eagle-4-0-1-3-ships-tokenspeed-and-f35898.md","json":"https://newruntime.com/posts/eagle-4-0-1-3-ships-tokenspeed-and-f35898.json"},"markdown_url":"https://newruntime.com/posts/eagle-4-0-1-3-ships-tokenspeed-and-f35898.md","next_reads":[{"type":"topic","path":"/topics/inference/","url":"https://newruntime.com/topics/inference/","title":"Inference","reason":"Explore the inference topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/inference.md","json_url":"https://newruntime.com/topics/inference.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}