AMD MI355X 首发支持 EAGLE-4 投机解码
AMD 与 EagleCorp 在 MI355X GPU 上 day-0 支持 EAGLE-4，启动时分析草稿与验证开销并动态选树，Qwen3.8-27B 单卡单请求约 300 tok/s，比内置 MTP 快 1.6 倍。
How do you make speculative decoding fast at any batch size? Let the drafter measure the hardware. Working with @EagleCorp, we've brought EAGLE-4 to AMD Instinct MI355X GPUs on day 0. EAGLE-Harness profiles drafting and verification costs at startup, then dynamically selects the optimal guess tree for the workload. On Qwen3.8-27B (BF16, single GPU): ⚡ ~300 tok/s single request ⚡ 1.6× faster than built-in MTP ⚡ Performance holds from 1-32 concurrent conversations ⚡ Lossless vs. plain decoding, including Gated DeltaNet layers via FlyDSL tree verification Details + launch scripts for SGLang and ATOM: https://www.amd.com/en/developer/resources/technical-articles/2026/eagle-4-on-amd-instinct-gpus.html