New DeepSeek inference stack released: how will it compare to vLLM, Modal, Together?
finbarrtimbers · x · 2026-10-20
DeepSeek released its new inference stack, and finbarr Timbers says he's very curious how it compares to Modal, Together, and vLLM. No benchmarks yet — the post is a question worth tracking as the open-source stack goes up against established inference providers.
More from Infra
- Mac Studio with 256GB RAM now shipping in 15-17 weeks as demand outstrips supply — LinusEkenstam · 2026-10-20
- Google open-sources TorchTPU to run PyTorch workloads on TPUs with minimal code changes — rseroter · 2026-10-20
- Simular's neuro-symbolic agent runs 217x cheaper than Opus at 72% on OSWorld — xwang_lk · 2026-10-20
- Ex-Google expert: data center capacity and electricity, not GPUs, are the real AI bottleneck — RihardJarc · 2026-10-20
- a16z hosts AI Infra Day with fal, Black Forest Labs, Krea and ElevenLabs engineers — venturetwins · 2026-10-20
- Video generation research runs on AMD MI350X, PRs merged into PyTorch nightly — vincesitzmann · 2026-10-20