Simon Willison releases LLM tool v0.37
Simon Willison released version 0.37 of his open-source LLM CLI tool and Python library. The update adds support for gpt-6.1 models and an OpenAI-compatible endpoint configuration command. The default model was switched to gpt-6-luna to reduce costs and improve embedding support.
Summarized by AI from one outlet
Source
- Simon WillisonRead original ↗
Latest
- Open source
Buoyant Releases Open-Source Inference Control Plane Kinference
Buoyant released Kinference, an Apache 2.0 licensed open-source inference control plane for Kubernetes and vLLM. It features declarative routing, KV-cache-aware load balancing, and reduced median TTFT by 95% in benchmarks.
- Open source
Ricursive Releases Open Model Ripple-65B
Ricursive Intelligence released Ripple-65B Preview, an open-weight model with 65 billion parameters. Licensed under Apache 2.0, the model reportedly achieved the top score among US open-source models on the TerminalBench 2.1 coding benchmark.
- Open source
Zyphra Releases ZYFA for AMD MI355X
Zyphra released ZYFA, open-source FP8 and BF16 prefill attention kernels for AMD MI355X. Its FP8 kernels run 1.16-1.76x faster than AMD's AITER with lower error.
All news → · All rights belong to the original creators