perf(qwen3.5-fp4-b200-sglang-mtp): enable FlashInfer GDN for TP2/EP2 / 为 TP2/EP2 启用 FlashInfer GDN (#2790)
* perf(qwen3.5): enable FlashInfer GDN for B200 TEP2 为 B200 上的 Qwen3.5 FP4 TP2/EP2 MTP 配置启用 FlashInfer GDN 后端。 * chore(perf-changelog): link Qwen3.5 GDN PR 回填 Qwen3.5 FP4 B200 FlashInfer GDN 变更的公开 PR 链接。 --------- Co-authored-by: Cam Quilici <cameron@semianalysis.com>
A
Ankur Singh committed
db7d21f38dec6dc04f7a417072e38f2bf5ff8e85
Parent: bdca939
Committed by GitHub <noreply@github.com>
on 9/1/2026, 8:35:44 PM