Reference Counting PyTorch Developer podcast

Artwork

Tech PyTorch Edward Yang Team PyTorch Deep Learning Machine Learning

Content provided by PyTorch, Edward Yang, and Team PyTorch. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by PyTorch, Edward Yang, and Team PyTorch or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ro.player.fm/legal.

PyTorch Developer Podcast « »
Reference counting

4+ y ago 15:14

Distribuie

MP3•Pagina episodului

Content provided by PyTorch, Edward Yang, and Team PyTorch. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by PyTorch, Edward Yang, and Team PyTorch or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ro.player.fm/legal.

Reference counting is a common memory management technique in C++ but PyTorch does its reference counting in a slightly idiosyncratic way using intrusive_ptr. We'll talk about why intrusive_ptr exists, the reason why refcount bumps are slow in C++ (but not in Python), what's up with const Tensor& everywhere, why the const is a lie and how TensorRef lets you create a const Tensor& from a TensorImpl* without needing to bump your reference count.

Further reading.

Why you shouldn't feel bad about passing tensor by reference https://dev-discuss.pytorch.org/t/we-shouldnt-feel-bad-about-passing-tensor-by-reference/85
Const correctness in PyTorch https://github.com/zdevito/ATen/issues/27
TensorRef RFC https://github.com/pytorch/rfcs/pull/16

… continue reading

83 episoade

#Tech #PyTorch #Edward Yang #Team PyTorch #Deep Learning #Machine Learning

Artwork

Reference counting

PyTorch Developer Podcast

26 subscribers

published 4+ y ago

Distribuie

MP3•Pagina episodului

Content provided by PyTorch, Edward Yang, and Team PyTorch. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by PyTorch, Edward Yang, and Team PyTorch or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ro.player.fm/legal.

Reference counting is a common memory management technique in C++ but PyTorch does its reference counting in a slightly idiosyncratic way using intrusive_ptr. We'll talk about why intrusive_ptr exists, the reason why refcount bumps are slow in C++ (but not in Python), what's up with const Tensor& everywhere, why the const is a lie and how TensorRef lets you create a const Tensor& from a TensorImpl* without needing to bump your reference count.

Further reading.

Why you shouldn't feel bad about passing tensor by reference https://dev-discuss.pytorch.org/t/we-shouldnt-feel-bad-about-passing-tensor-by-reference/85
Const correctness in PyTorch https://github.com/zdevito/ATen/issues/27
TensorRef RFC https://github.com/pytorch/rfcs/pull/16

… continue reading

83 episoade

#Tech #PyTorch #Edward Yang #Team PyTorch #Deep Learning #Machine Learning

Tutti gli episodi

×

Bun venit la Player FM!

Player FM scanează web-ul pentru podcast-uri de înaltă calitate pentru a vă putea bucura acum. Este cea mai bună aplicație pentru podcast și funcționează pe Android, iPhone și pe web. Înscrieți-vă pentru a sincroniza abonamentele pe toate dispozitivele.

Ascultă peste 500 de subiecte

Ghid rapid de referință

Podcast-uri de top

Florin Rosoga Podcast

Morning Glory cu Răzvan Exarhu

Epic Show Podcast

UPGRADE 100 Podcasts

România în direct - Europa FM

Deşteptarea - Europa FM

Ajutor/FAQ | Upgrade | Advertise

Arte|Afaceri|Comedie|Economie|Divertisment|Știri|Politică|Religie

Ştiinţă|Fotbal|Sport|Povestiri|Tehnologie|True Crime

Drepturi de autor 2025 | Politica de confidenţialitate | Termenii serviciului | | Copyright

Listen to this show while you explore