PyTorch 2.5 Live Q&A
30:06
PyTorch 2.6 Release Live Q&A
20:37
State of PyTorch - Ji Li & Damien Sereni, Meta
29:18
PyTorch Expert Exchange Hacker Cup AI
33:29
How does batching work on modern GPUs?
44:06
LLM inference optimization: Architecture, KV cache and Flash attention
24:21
Running State-of-Art Gen AI Models on-Device with NPU Acceleration - Felix Baum, Qualcomm
32:03
DistServe: disaggregating prefill and decoding for goodput-optimized LLM inference
27:14