RT clem 🤗Big unlock for open-source AI inference: Hugging Face Transformers models can now run in vLLM at native speed, often matching or beating hand-written implementations.Until…
RT Benjamin MarieThinkingCap-Qwen3.6-27B is really good.Much faster than the original Qwen3.6-27B thanks to shorter thinking, while preserving accuracy.Also one of the best evaluation I have seen…
RT falWe've open sourced Ideogram V4 instant and fast, find them here!Fast: https://huggingface.co/fal/ideogram-v4-fastInstant: https://huggingface.co/fal/ideogram-v4-instantTry them out for free on fal right now: https://fal.ai/sandbox?models=d95roj4regjbfne461fg,d940ircregj6fnrjnja0fal: http://x.com/i/article/2076691
RT Sayak PaulWe show that best-of-N (BoN) is a much better baseline for diffusion test-time scaling when done right.Our core premise is that NFEs provide a…
RT David LouapreWith J-Space, Anthropic has managed to monitor Claude’s internal thoughts. Again? It feels as though we have heard that claim several times already! Ah…
RT Novita AIWe trained and released DSpark speculators for Kimi-K2.6 and Kimi-K2.7-Code on @huggingface, with native serving support in @vllm_project.Across six benchmarks in our batch-size-1 evaluation:Kimi-K2.6:…
RT apolinario (poli)GPUs for all 🤗Creating ZeroGPU demos or apps is now available to ALL @huggingface userstell your agent: "Build a HF ZeroGPU demo for this…
RT apolinario (poli)GPUs for all 🤗Creating ZeroGPU demos or apps is now available to ALL @huggingface userstell your agent: "Build a HF ZeroGPU demo for this…
RT Sayak PaulRemember, the coolest event of the week is happening on the 15th. Those who have got their registrations confirmed, we're looking forward to building…
RT clem 🤗The same way, we're probably one of the few AI startups with user network effects, we might become the first one with agent network…