Hugging Face switches language model inference to OpenRouter's smart routing
Hugging Face now routes language model requests through OpenRouter, which selects the best provider by live price, speed, and reliability and retries on failure.
AI news and practical stories about this company.
Hugging Face now routes language model requests through OpenRouter, which selects the best provider by live price, speed, and reliability and retries on failure.
Google introduces TPU 8tx for secure, confidential inference and TPU 8i Max for massive context windows and high compute density.
The 65–75 MB model covers five languages, tops German and Spanish intelligibility, and leads CPU streaming speed benchmarks
FP8 tensors on MPS: 5–6.5× MoE decoding speedups; Wan2.2 video VAE memory drops from ~270 GiB to 8 GiB; softmax ~8× faster; complex64 LU factorization added.
Hugging Face’s Open TTS Leaderboard compares open TTS models using WER/CER, RTFx, TTFA and speaker similarity. Its scores complement rather than replace human preference rankings.