INFERENCE LAB / TAGS

SGLang

Technical notes organized around a shared topic.

Inference

Distinguish the attention state stored during generation from reuse of that state across requests.

Sep 7, 2026 · 2 min read

Reference guide · awaiting lab validation

Inference

A deployment validation plan for Qwen3.8-27B, covering hardware inventory, version pinning and a reproducible acceptance test.

Sep 7, 2026 · 2 min read

Reference guide · awaiting lab validation

Inference

Separate speculative decoding concepts from model- and release-specific launch options.

Sep 7, 2026 · 2 min read

Reference guide · awaiting lab validation

Inference

Choose an inference engine using workload compatibility, reproducibility and operational requirements—not an unqualified leaderboard.

Sep 7, 2026 · 2 min read

Reference guide · awaiting lab validation