$ tail -f topics/llms.log
Daily updates from the local-LLM inference stack - Ollama, llama.cpp, vLLM, and SGLang. What shipped this week in running and serving open models on your own hardware.
11 updates across 2 projects this week.
One calm review of what shipped across Local LLMs - the commits, releases, and security advisories that matter. Every Monday, with security advisories same-day. Free, unsubscribe in one click.
We'll start you on the top Local LLMs projects - refine anytime. · Read a sample issue →
Local LLMs
Qwen3.5's MTP head is now live across both Ollama and llama.cpp, delivering 24-70% inference speedup on dense models while Ollama adds smart cloud-model routing to end user confusion.
read --wire →
Local LLMs
llama.cpp plugged a critical conversation data loss hole, while vLLM synchronized CPU kernels with upstream sglang and shipped Kimi K3 support across the local LLM stack.
read --wire →
Local LLMs
Ollama's CI now scans the entire codebase instead of just changed lines, unblocking larger PRs that were silently accumulating lint violations across their diffs.
read --wire →
Local LLMs
Ollama removed its entire MLX image generation pipeline overnight, while llama.cpp landed DSpark speculative decoding and fixed a critical SYCL memory bug affecting Arc GPUs.
read --wire →
Local LLMs
Ollama shipped three performance wins for the terminal interface while llama.cpp redefines mlock semantics and vLLM closes quant bugs across ROCm and transformer backends.
read --wire →
Local LLMs
The inference stack gets a new model architecture and a fundamental shift in how prefill and decode can run on different hardware configurations.
read --wire →
Local LLMs
llama.cpp disabled OpenMP for Emscripten builds to fix WASM compilation, while shipping full MCP stdio support and unlocking 1.5x to 3.5x latency gains on Hexagon vision models.
read --wire →
Local LLMs
Ollama shipped three critical performance and reliability fixes for Metal residency and concurrent access patterns, while SGL-Lang released 0.5.16 with a new speculative algorithm hitting 383.7 tok/s on DeepSeek-V4.
read --wire →
Local LLMs
The inference stack is consolidating around speculative decoding, and the bugs surfacing there are getting squashed across three major projects simultaneously.
read --wire →
Local LLMs
Ollama shipped a skills import system that lets coding agents pull validated skill directories from external sources, while simultaneous fixes to GLM tool-call parsing and Laguna model alignment prevent agents from silently failing.
read --wire →
