Inferact · od January 22, 2026 (Inferact public launch, $150M seed) · 2× · naposledy 18. 10. 2026
31
Momentum
vLLM is an open-source inference and serving engine for large language models, originally developed at UC Berkeley and now managed by the PyTorch Foundation. The company Inferact, founded by vLLM's maintainers, offers a commercial production layer built on vLLM. The engine supports NVIDIA, AMD, Intel, Apple Silicon, CPU and TPU hardware, plus an OpenAI-compatible server.
Vývoj momenta
20.07.18.10.
Vlastnosti
| License | Apache 2.0 (vLLM project, PyTorch Foundation) |
| Platform | NVIDIA CUDA, AMD ROCm, Intel XPU, Apple Silicon, CPU (x86, ARM), IBM Z; Google TPU |
| Protocol Compatibility | OpenAI-compatible HTTP server (/v1/chat/completions, /v1/completions, /v1/models) |
| Release Date | January 22, 2026 (Inferact public launch) |
| Supported Models/Providers | More than 300 model architectures per Inferact press release (Oct 2026); 500+ per Inferact blog (Jan 2026) |