LMSYS Releases SpecForge Update: Advanced Speculative Decoding for Major Models
BanghuaZ · x · 2026-08-05
LMSYS released SpecForge v0.3.0, bringing major updates to speculative decoding.
- Architecture Upgrade: The new runtime separates target-model inference from draft-model training, unifying online, offline, and disaggregated workflows.
- Model Support: SpecBundle expands to 11 open draft models, covering major models like GLM-5.1, Kimi K2.5/K2.6/K2.7-Code, Qwen3, and Step-3.5-Flash.
More from Infra
- YC-Backed Lamb Labs Claims 63x Higher Efficiency for AI Inference Chips vs GPUs — ycombinator · 2026-08-05
- DSpark Open-Sources Speculative Decoding Path for Kimi K3 — ying11231 · 2026-08-05
- US Drafts Ban on Chinese Datacenter Components as Europe Pushes for Tech Sovereignty — nordicinst · 2026-08-05
- Cursor Releases Mixture-of-Kittens Megakernel for MoE, Claims Nearly 2x TFLOP/s — CapnHat · 2026-08-05
- NVIDIA Tutorial: Building Fully Local Autonomous Agents on Jetson — NVIDIA Developer · 2026-08-05
- YC Launches Caution Hosting: Secure Enclaves for Sensitive AI Workloads — ycombinator · 2026-08-05