Fireworks launches Ultra-fast inference up to 1,500 tok/s and half-price background mode at Forge
nicolechirps · x · 2026-11-04
At its first Forge conference, Fireworks unveiled new products: Ultra-fast inference up to 1,500 tok/s on NVIDIA Blackwell, half-price Background Mode, Nexus subscriptions from $8/month, LoRA-based specialized inference without GPU deployment, Fireworks Sovereign (its engine on customer GPUs), and No Eval auto-evals from production traces — pitching open-weight ensembling plus custom training as an alternative to closed frontier labs.
Related event: Fireworks unveils ultra-fast inference and sovereign AI stack(2 posts)→
More from Infra
- mlx-serve PR runs DeepSeek-V4.1 tensor-parallel across two Macs, 57% faster decode — HankYeomans · 2026-11-04
- PyTorch Day Japan 2026 agenda drops: ExecuTorch porting to IBM AIU edge accelerator — PyTorch · 2026-11-04
- LFM3 d1-2b decision model runs locally on Raspberry Pi at ~9s per decision — JosephJacks_ · 2026-11-04
- Inference Engine Explosion: llama.cpp Loyalist Can't Keep Up With New Frameworks — Kahvana · 2026-11-04
- One RTX 6000 Pro now out-earns the average human: $29,696/year in rent vs $23,000 global mean income — KyeGomezB · 2026-11-04
- Concurrency limits are the hidden tax in voice AI — how Phonic solved it — graceisford · 2026-11-04