Furuichi Station
PulseAugur coverage of Furuichi Station — every cluster mentioning Furuichi Station across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
osFoundry's Local Model simplifies running and tuning open LLMs locally
osFoundry's Local Model is a desktop application designed to manage open-weight language models on a user's own hardware. It integrates model exploration, downloading, fine-tuning, quantization, and evaluation within a …
-
Quantizing KV cache in Ollama slows down Qwen3 coder 30b but boosts context capacity
An experiment with Ollama on an RTX Spark GPU explored the impact of quantizing the KV cache for the Qwen3 coder 30b model. While 8-bit and 4-bit quantization significantly reduced memory usage, allowing for much larger…
-
llama.cpp releases optimizations, new ops; contrastive learning research published
The llama.cpp project has released two pre-release versions, b11936 and b11840, introducing optimizations and new operations. Version b11936 focuses on improving the k-pool sparse selection for models like Qwen4Exp and …
-
llama.cpp PR boosts prompt processing with vectorized F16-F32 conversion
A pull request to the llama.cpp project introduces vectorized conversion of F16 to F32 for Flash Attention V-Cache. This optimization leverages hardware F16C intrinsics, resulting in a significant performance boost. Spe…
-
llama.cpp PR caches MoE experts for faster local AI inference · 4 sources tracked
A new pull request for llama.cpp introduces a method to cache frequently used Mixture of Experts (MoE) layers on the GPU, significantly boosting inference speeds for models like Qwen3.6-35B-A3B by up to 2x on consumer h…