Similares a Performance Optimization and Software/Hardware Co-design across PyTorch, CUDA, and NVIDIA GPUs

20 vecinos (text_768) · 669 views · MLOps.community · Reino Unido


★	Performance Optimization and Software/Hardware Co-design across PyTorch, CUDA, and NVIDIA GPUs	MLOps.community @mlops	669	Reino Unido
10	Let's Build Pipeline Parallelism from Scratch – Tutorial	freeCodeCamp.org @freecodecamp	—	Estados Unidos	88
13	Coordinating Secure GPU-Accelerated Agents with Foundry Control Plane on Azure [APAC]	Microsoft Reactor @microsoftreactor	—	—	88
1	Lessons From Training Composer At Cursor And Building Meta/Nvidia Compute Clusters \| YC Paper Club	Y Combinator @ycombinator	68.6K	Estados Unidos	90
19	Optimizing the Full Stack for Generative Image and Video Models	MIT OpenCourseWare @mitocw	12.1K	Estados Unidos	87
9	Every AI Company Runs on NVIDIA Because of One Decision Made in 2006!	Manav @manavgolecha	6.0K	Estados Unidos	88
15	WWDC26: Optimize custom machine learning operations with Metal tensors \| Apple	Apple Developer @appledeveloper	4.7K	—	88
4	Stanford CS25: Transformers United V6 I The Ultra-Scale Talk: Scaling Training to Thousands of GPUs	Stanford Online @stanfordonline	4.6K	Estados Unidos	89
20	Data Science Gamechanger?	Rob Mulla @robmulla	2.5K	Estados Unidos	87
18	Passer à la vitesse supérieure : Optimisation avancée de l'apprentissage (épisode 18)	CNRS - Formation FIDLE @cnrs-fidle	1.2K	Francia	87
17	How We Cut LLM Latency 70% With TensorRT in Production	MLOps.community @mlops	697	Reino Unido	87
2	Fixing GPU Starvation in Large-Scale Distributed Training	MLOps.community @mlops	321	Reino Unido	89
7	The MATH of Running Humanity on GPUs (It's Cheap!)	Finxter AI Nuggets @finxter	138	Alemania	88
14	Edge Driven Generative AI Hardware Poised to Redefine Real Time Design	new technology insights @newtechnologyinsights-i9o	135	—	88
11	Quantum Gradient Descent Accelerating Machine Learning Beyond Classical Computational Hardware Limit	NobleX Infinity Labs®️ @noblexinfinitylabs	108	India	88
8	LOCA series: TuRTLe: Artificial Intelligence for Chip Design research at BSC	BSC CNS @bsccns	73	España	88
6	The Real AI Bottleneck It’s Not GPUs It’s Memory Design and Math	NextGen Science @thenextgenscience	67	Estados Unidos	88
5	Optimize GPU Geometry with meshoptimizer: Complete Pipeline Explained	Alex Hitt @alexander-hitt	57	Estados Unidos	88
12	LOCA series: Optimal Silicon Efficiency in Servers	BSC CNS @bsccns	43	España	88
16	Understanding GPUs, TPUs, NPUs, and specialized AI chips (10 Minutes)	Microlearning Daily @microlearningdaily	31	Singapur	87
3	Showcasing WASM GPU Offload APIs	Intel Open Source @intelopensource	4	Estados Unidos	89