@ariG23498: Made a simple utility to share your GPU profile traces. `uvx trace-tuil <local traces> -b <hf bucket name>`
Summary
A simple utility to share GPU profile traces using a command-line tool, designed for developers working with GPU profiling.
View Cached Full Text
Cached at: 05/15/26, 11:09 PM
Made a simple utility to share your GPU profile traces.
uvx trace-tuil <local traces> -b <hf bucket name> https://t.co/tLYc2JegJW
Similar Articles
I built an open-source tool that reduces TensorBoard trace sizes by 90%+ for JAX/XLA (XProf Cubism Reducer)
An open-source tool called XProf Cubism Reducer reduces TensorBoard trace sizes by over 90% for JAX/XLA, making performance profiling more efficient.
janestreet/magic-trace
magic-trace is a high-resolution tracing tool using Intel Processor Trace to capture full control flow snapshots of Linux processes with low overhead, useful for debugging and performance analysis.
@sudoingX: save this one. it answers a question every 24gb GPU owner asks and almost nobody gets right. how much context can i act…
A user shares detailed VRAM usage measurements for running Qwen 3.6 27b on a 24GB GPU, showing context window sizes and headroom, and notes that a used RTX 3090 performs identically to newer cards.
@leopardracer: https://x.com/leopardracer/status/2055341758523883631
A user shares their experience setting up a dual-GPU local AI lab with RTX 4080 Super and 5060 Ti, running Qwen 3.6 models via llama.cpp and llama-swap to reduce API costs and enable unrestricted experimentation.
xdna-top: unified NPU+iGPU terminal monitor for Strix Halo (Ryzen AI Max) — finally see the NPU work
xdna-top is a terminal monitor that shows both NPU and iGPU activity on Ryzen AI Max/Strix Halo systems, providing an honest view of NPU counter deltas instead of fake utilization percentages.