GoKawiil
1-Bit Bonsai Image 4B Image Generation for Local Devices
(news.ycombinator.com)
61.
62.
Show HN: Tiny-vLLM – high performance LLM inference engine in C++ and CUDA
(news.ycombinator.com)
63.
64.
65.
Real-time LLM Inference on Standard GPUs: 3k tokens/s per request
(news.ycombinator.com)
66.
Has the hunt for AI compute uncovered the next Cerebras?
(techcrunch.com)
67.
Stress disrupts hippocampal integration of overlapping events, memory inference
(news.ycombinator.com)
68.
Use boring languages with LLMs
(news.ycombinator.com)
69.
Use Boring Languages with LLMs
(news.ycombinator.com)
70.
The current AI pricing was always going to go away
(news.ycombinator.com)
71.
Cutting inference cold starts by 40x with LP, FUSE, C/R, and CUDA-checkpoint
(news.ycombinator.com)
72.
KV Cache Is Becoming the Memory Hierarchy of Inference
(news.ycombinator.com)
73.
UK sovereign LLM inference
(news.ycombinator.com)
74.
76.
Abstract Machines for Logic Programs
(news.ycombinator.com)
77.
AI Computing Is a Memory Hog. An Nvidia-Backed Startup Has an Answer.
(feeds.content.dowjones.io)
78.
Nicolas Sauvage is betting on the boring parts of AI
(techcrunch.com)
79.
80.
Cheaper tokens, bigger bills: The new math of AI infrastructure
(venturebeat.com)
81.
82.
Claude Code removed from Anthropic's Pro plan
(news.ycombinator.com)
83.
Kimi vendor verifier – verify accuracy of inference providers
(news.ycombinator.com)
84.
Zero-Copy GPU Inference from WebAssembly on Apple Silicon
(news.ycombinator.com)
85.
86.
Cloudflare's AI Platform: an inference layer designed for agents
(news.ycombinator.com)
87.
88.
Age verification is a mess but we’re doing it anyway
(theverge.com)
89.