LMSYS (Large Model Systems Organization) — USASI news https://unitedstatesofamericasuperintelligence.com/companies/lmsys/ Dated, sourced news items in the USASI catalog that mention LMSYS (Large Model Systems Organization). Independent project. Not a United States government website. en-us Tue, 20 Oct 2026 12:00:00 GMT SGLang 0.5.22 adds Apple Silicon support with the PyTorch backend and an InstantTensor loader https://unitedstatesofamericasuperintelligence.com/news/sglang-0-5-22-released/ https://unitedstatesofamericasuperintelligence.com/news/sglang-0-5-22-released/ Tue, 20 Oct 2026 12:00:00 GMT release The SGLang project published v0.5.22 on GitHub on October 19, 2026. The release notes say SGLang now runs on Apple Silicon Macs with the standard PyTorch backend, alongside MLX, that a new InstantTensor loader speeds up model loading, and that HiSparse now supports EAGLE and MTP for long-context serving with the KV cache in CPU memory. Newly supported models listed include Clef / Clef Flash, PPLX-Decider v1 / v1.1, EmbeddingGemma 2, Kandinsky 6 and SANA-Video 2.0. The notes say SGLang now requires Python 3.11 or newer, and describe a fix for hybrid linear models that could resume from wrong mamba states when speculative decoding and structured output were used together. USASI has not tested these changes. SGLang 0.5.21 adds a Decisions API and runtime prefill-decode role switching https://unitedstatesofamericasuperintelligence.com/news/sglang-0-5-21-released/ https://unitedstatesofamericasuperintelligence.com/news/sglang-0-5-21-released/ Tue, 13 Oct 2026 12:00:00 GMT release The SGLang project published v0.5.21 on GitHub on October 2, 2026. The release notes highlight prefill-decode instances that can switch between prefill and decode without a restart, a Rust core for the prefix cache by default, a new Decisions API (/v1/decisions) that lets an LLM or VLM act as a low-latency classifier and scorer, and a Score API (/v1/score) that scores all candidates in one request. Under breaking changes, request-supplied chat_template values are rejected unless the server starts with --trust-request-chat-template, and deprecated endpoints, environment variables, and aliases, along with legacy radix cache implementations, were removed. The release also adds support for models including DeepSeek-V4.1 Flash and MiMo-V2.6. USASI has not tested these changes.