llama.cpp release b9437 adds support for `-fa auto` in llama-bench, sets the default value of `-ngl` to -1, and includes README updates and macOS/iOS…
OriginalAI Intel
Last 90 days · 2931 total
vLLM v0.22.1rc0 has been released, focusing on CI improvements to make Model Executor test hangs fail faster with a traceback.
OriginalOpenAI Codex has released Python SDK version 0.1.0b2, indicating continued development and updates to its developer tools.
OriginalNVIDIA has released the Qwen3.6-35B-A3B-NVFP4 model on Hugging Face, which is a quantized version of Alibaba's Qwen3.6-35B-A3B auto-regressive langua…
OriginalAnthropic's Claude Code v2.1.154 introduces Opus 4.8, defaulting to high effort for complex tasks and enabling dynamic workflows orchestrated across…
OriginalAnthropic announced the acquisition of StainlessAPI, the SDK and MCP server platform that has supported all Anthropic SDKs since the early days of it…
OriginalGrok Build is now in beta for SuperGrok and X Premium+ users, offering Plan Mode, image/video creation with Imagine, and automation building via CLI.
OriginalMistral Vibe has shipped as an AI agent designed for long-horizon productivity and coding, featuring Work mode, Code mode, a CLI, and a new VS Code e…
OriginalMeta's new Muse Spark model scored 52 on the Artificial Analysis Intelligence Index, positioning it behind Gemini 3.1 Pro, GPT-5.4, and Claude Opus 4…
OriginalGoogle has made its Nano Banana 2 and Nano Banana Pro image generation models generally available to developers and businesses via Google AI Studio a…
Original