Ant Group and vLLM open-source Humming quantization kernels
Ant Group and the vLLM community have open-sourced Humming, a quantized inference kernel library that compiles in seconds and lifts DeepSeek-V4.1-Flash throughput on 8 H20 GPUs.
Inference News and Analysis
5 verified stories covering Inference, product updates and industry developments.
SambaNova raises $1 billion at an $11 billion valuation
SambaNova raises $1 billion at an $11 billion valuation is reframed for global technology readers, with the key numbers, product claims and open questions kept intact.
Baseten raises $1.5B as inference becomes the prize
Baseten’s new Series F values the inference infrastructure company at up to $13 billion, reflecting investor demand for cheaper, faster and more reliable model serving.
Gemini 3.1 Pro tops 12 out of 18 benchmarks
Google DeepMind's Gemini 3.1 Pro leads in 12 of 18 tracked benchmarks, with a standout 77.1% on ARC-AGI-2 for novel reasoning. The model doubles inference capabilities over its predecessor, adds a medium thinking level, and supports up to 1M token context, but trails GPT-5.4 Pro and Claude Opus 4.6 in overall composite scores and coding tasks.
Kimi K1.5 validates reinforcement learning-driven reasoning
Moonshot AI's K1.5 model, released before K2, demonstrates that pure reinforcement learning can enhance reasoning capabilities, validating the approach for scaling to larger models.