Run any command on a remote GPU from your terminal
Boulder, Colorado
Joined April 2025
- Tweets104
- Following106
- Followers28
- Likes679
GPU CLI retweeted
Really enjoying working with the new #attn changes that allow me to share thoughts on html files.
They're agent agnostic and allows me to quickly provide artefact feedback.
GPU CLI retweeted
Really enjoying using the new `clean-comments` skill we made. It's helped reduce a lot of noise in my recent PRs
GPU CLI retweeted
Windows development is actually fun
- @unity 's Parsec + Windows Terminal + Claude Code (or Codex)
- No RAM bloat from WSL running in the background.
Mostly been working on inference for windows.
GPU CLI `0.32.0` has native windows support so bursting into the cloud works nicely too
GPU CLI retweeted
What was used to rewrite Bun into Rust apparently
GPU CLI retweeted
I wanted faster builds so I explored how to conditionally build our rust monorepo based on the cargo dependency graph - packaged it up as a github action for reuse across projects github.com/lightsofapollo/ca…
GPU CLI retweeted
To check if your Google Workspace has been compromised by the same tool that compromised Vercel:
1. Go to admin.google.com/ac/owl/list…
- This is Google Admin Console > Security > Access and Data Control > API Controls > Manage app access > Accessed Apps
2. Filter by ID = 110671459871-30f1spbu0hptbs6…
- This is the ID of the compromised OAuth app
If you see an app after filtering, you have potentially been compromised
GPU CLI retweeted
We're proud to share that @NVIDIA submitted the first-ever MLPerf Vision Language Model (VLM) performance benchmark using vLLM. This achievement showcases the strength of our ongoing collaboration with NVIDIA Engineering.
Check out their MLPerf blog and watch our On Demand Talk at GTC to learn more about how we are delivering the best performance on NVIDIA hardware.
🔗 Blog: developer.nvidia.com/blog/nv…
🔗 Talk: nvidia.com/en-us/on-demand/s…
Open-source software never stops. It only accelerates.
Dynamo, @sgl_project, TensorRT LLM, and @vllm_project are constantly optimized by a vast ecosystem of developers building on top of the NVIDIA platform.
The result: your token output keeps improving and token cost keeps decreasing on the same hardware resources while your developer velocity stays at its peak.
Build on the foundation continuously optimized by the world’s best developers. ⚡
🔗 nvda.ws/3OsTQL0
GPU CLI retweeted
Introducing Kitten TTS V0.8: open-source TTS that fits in 25MB.
Three variants: 80M | 40M | 14M (<25MB)
Highly expressive. Runs on CPU. Built for edge.
No GPU? No problem. Ship voice anywhere.
Check it out:
GPU CLI retweeted
🎉 Congrats to @MistralAI on releasing Mistral Small 4 — a 119B MoE model (6.5B active per token) that unifies instruct, reasoning, and coding in one checkpoint. Multimodal, 256K context.
Day-0 support in vLLM — MLA attention backend, tool calling, and configurable reasoning mode, verified on @nvidia GPUs.
🔗 huggingface.co/mistralai/Mis…
GPU CLI retweeted
Reve is now available in ComfyUI!
This model delivers strong aesthetics and can generate dynamic, high quality images at up to 4k resolution.
Reve Create generates images in 5 seconds, allowing for fast iteration and further refinement using the Reve Edit or Reve Remix nodes.
Check out more examples below!
GPU CLI retweeted
Alibaba’s Qwen 3.5 is now running fully on-device on the iPhone 17 Pro.
It outperforms models 4x its size, delivers strong visual understanding, and lets you switch reasoning on or off.
This demo uses the 2B 6-bit version, optimized with MLX for Apple Silicon.
GPU CLI retweeted
🤯Real-time video generation just got HUGE.
Introducing Helios: A 14B parameter model running at 19.5 FPS on a single H100.
Cheaper, Faster, and Stronger than 1.3B models, generating minute-long videos without the usual tricks (even no quantization).
github.com/PKU-YuanGroup/Hel…
GPU CLI retweeted
NEW: Alibaba just released Qwen 3.5 Small — a family of powerful multimodal models available in a range of sizes (0.8B, 2B, 4B, and 9B parameters). Perfect for on-device applications!
They can even run 100% locally in your browser on WebGPU, powered by Transformers.js! 🤯
GPU CLI retweeted
CLIs are super exciting precisely because they are a "legacy" technology, which means AI agents can natively and easily use them, combine them, interact with them via the entire terminal toolkit.
E.g ask your Claude/Codex agent to install this new Polymarket CLI and ask for any arbitrary dashboards or interfaces or logic. The agents will build it for you. Install the Github CLI too and you can ask them to navigate the repo, see issues, PRs, discussions, even the code itself.
Example: Claude built this terminal dashboard in ~3 minutes, of the highest volume polymarkets and the 24hr change. Or you can make it a web app or whatever you want. Even more powerful when you use it as a module of bigger pipelines.
If you have any kind of product or service think: can agents access and use them?
- are your legacy docs (for humans) at least exportable in markdown?
- have you written Skills for your product?
- can your product/service be usable via CLI? Or MCP?
- ...
It's 2026. Build. For. Agents.
