GreenGames
- Karma
- 0
- Created
- ()
- Submissions
- 0
- 256K context with 72MiB of KV cache on the GPU (github.com)
- A 35B MoE on a 16 GB GPU, without the offload tax (lucebox.com)
- We got 207 tok/s with Qwen3.5-27B on an RTX 3090 (github.com)
-
Hey there, we fused all 24 layers of Qwen3.5-0.8B (a hybrid DeltaNet + Attention model) into a single CUDA kernel launch and made it open-source for everyone to try it. On an RTX 3090 power-limited to 220W: - 411 tok/s…
- Cua (YC X25) is hiring an engineer (ycombinator.com)
- Show HN: Lumier – Run macOS VMs in a Docker (github.com)
Hey HN, we're excited to share Lumier (https://github.com/trycua/cua/tree/main/libs/lumier), an open-source tool for running macOS and Linux virtual machines in Docker containers on Apple Silicon Macs. When building…
- Microsoft is reportedly about to lay off 3% of its workforce (techcrunch.com)
- Polaris is giving free GPUs/CPUs for everyone (polariscloud.ai)
- Microsoft and OpenAI are renegotiating their partnership (techcrunch.com)
- Apple developing new chips for smart glasses, Macs, and more (techcrunch.com)
-
Shoutout to our amazing contributor @iaktech for building tlume - a CLI tool that converts Tart VM images into the format expected by Lume! tlume will: - Locate your Tart VM in ~/.tart/vms/ - Create a Lume VM in…
-
We just open-sourced Lume - a tool we built after hitting walls with existing virtualization options on Apple Silicon. No GUI, no complex stacks - just a single binary that lets you spin up macOS or Linux VMs via CLI or…
- Show HN: List of AI Agents (github.com)
- A curated list of AI agents for Computer Use (github.com)
- ACU – Agents for Computer Use (github.com)
- An AI Code Assistant into Your IDE (safurai.com)