Hugging Face launches a PyTorch profiling series: from torch.profiler to attention
ariG23498 · x · 2026-10-11
Hugging Face published a new tutorial series on PyTorch profiling. Part 1 is a beginner's guide to torch.profiler—setting it up and reading the table and traces (CPU lane, GPU lane, and suspicious gaps). Upcoming parts cover fusing MLPs and profiling attention. Question-led and prerequisite-free, aimed at engineers optimizing LLM inference and training speed.
More from Infra
- AirLLM runs 70B models on a 4GB GPU via layer-wise inference, scaling to 405B on 8GB — JensHonack · 2026-10-11
- Speech Model Shrunk 13x to 153M Params by Looping 2 Shared Blocks — pbaylies · 2026-10-11
- Inference demand went vertical, yet is a flat line next to post-training/RL growth — zainhas · 2026-10-11
- Pat Gelsinger slams HBM as "a lousy memory" wasting four bits for every one it makes — SumitGup · 2026-10-11
- Qualcomm CEO predicts AI phone supercycle, smart glasses as top AI wearable — SuB8u · 2026-10-11
- Zero cold starts: Building and shipping MCP servers with WebAssembly, Spin and Akamai Functions — AI Engineer · 2026-10-11