lucasgelfond/zerobrew

alyraffauf/blzrd

Blazing flast deployments for NixOS + nix-darwin.

Jacky Kwok on Twitter / X

Scaling self-verification with DeepSeek V4 Flash beats Claude Fable 5 on Terminal-Bench 2.1, while being 11x cheaper 💰As open-source models become more capable, they can now generate large numbers of high-quality candidate solutions and verify their own outputs at very low… https://t.co/as2HtyHzzW pic.twitter.com/XzVBgr5JPz— Jacky Kwok (@jackyk02) August 17, 2026

0xSero on Twitter / X

I told y’all this is the move. Heterogenous hardware is the way forward. Large cheap pools of mixed memory + specialized accelerators (Nvidia GPUs, DGX Spark, Cerebras wafers) The next year will be dominated by solutions that split the stack. - 3000$ for a used Mac Studio… https://t.co/zMlScSnJ0X— 0xSero (@0xSero) April 1, 2026

Compiling Models to Megakernels

Fine-grained synchronization, deep pipelines, and zero kernel launch overheads, automatically.

Homebrew

The Package Manager for Everywhere.

7.0.0

Today, I’m proud to announce Homebrew 7.0.0. The most significant changes since 6.0.0 are faster installations and upgrades, stronger sandboxing, a native macOS app, built-in vulnerability checks and an advisory database, the end of macOS 10.15 support and Intel Macs moving to Tier 3.

OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show | TechCrunch

Tested on SemiAnalysis’ InferenceX benchmark, Jalapeño registered both more tokens per user and more throughput per kilowatt than the currently available state-of-the art.

Combining NVIDIA DGX Spark + Apple Mac Studio for 4x Faster LLM Inference with EXO 1.0

Disaggregating Prefill and Decode: Faster First Tokens, Faster Streams

Combining NVIDIA DGX Spark + Apple Mac Studio for 4x Faster LLM Inference with EXO 1.0

Disaggregating Prefill and Decode: Faster First Tokens, Faster Streams

ali on Twitter / X

was skeptical but gave it a shot because @karpathyanyways 2x kernel perf (fp4 matmul)3 minutes of work (1 prompt)triton beat cutlass (?!) https://t.co/HGIpP4OoNG pic.twitter.com/N9KHrDsFz2— ali (@waterloo_intern) March 11, 2026

For dual DGX spark users; GLM 5.3 flash got a 50%+ performance boost

For the last few months, I ran DeepSeek v4.0 flash (NVFP4). First 0731, then visionexp because it was a free improvement. I got around 65 tps decode…

jazware/bsky-experiments

A mirror of my personal monorepo's AT Proto tools

raullenchai/Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

raullenchai/Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

Faster double-to-string conversion

There comes a time in every software engineer’s life when they come up with a new binary-to-decimal floating-point conversion method. I guess my time has come. I just wrote one, mostly over a weekend: https://github.com/vitaut/zmij.