PyTorch

(updated 2 days ago)

Timeline

Jump To

14 Nov 2024 (GMT)
How does batching work on modern GPUs?33:29
expand...

22 Oct 2024 (GMT)
PyTorch 2.5 Live Q&A01:00:55
expand...

17 Oct 2024 (GMT)
DistServe: disaggregating prefill and decoding for goodput-optimized LLM inference32:03
expand...

12 Oct 2024 (GMT)
Efficient Streaming Language Models with Attention Sinks35:50
expand...

09 Oct 2024 (GMT)
PyTorch Conference 2024 Highlights01:41
expand...

01 Oct 2024 (GMT)
[HALIDE] A Halide Backend for TorchInductor - Jason Ansel, Meta08:09
expand...
Lightning Talk: Mobile Computational Photography with PyTorch: Low-Light Denoising - Alexis Baudron08:28
expand...
State of PyTorch - Ji Li & Damien Sereni, Meta20:37
expand...
Lightning Talk: Sparsifying Vision Transformers with Minimal Accuracy Loss - Jesse Cai, Meta14:02
expand...
[TVM] Universally Deploy Large-language Models via ML Compilation - Tianqi Chen, CMU & OctoAI10:50
expand...

Load More