Skip to content

Pull requests: triton-inference-server/pytorch_backend

New pull request New
7 Open 203 Closed
7 Open 203 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

build: Update C++ standard from c++17 to c++20 build Build system or external dependencies (build: PRs)
#210 opened Sep 9, 2026 by mc-nv Contributor Loading…
8 of 20 tasks
@mc-nv
3
Add support where torchscript model outputs a dictionary of tensors
#174 opened Nov 16, 2025 by chdhr-harshal • Draft
2
Added cpu only support.
#171 opened Nov 12, 2025 by Sunidhi-Gaonkar1 • Draft
1
Enable configurable deterministic algorithm flag
#150 opened May 5, 2025 by yhna940 Loading…
Run in default mode when inference mode is disabled
#146 opened Jan 23, 2025 by hakanardo Loading…
Setting max_gpu_fraction as in Tensorflow backend
#108 opened May 22, 2023 by FabianSchuetze Loading…
2
Support calling custom method names on PyTorch module
#99 opened Apr 8, 2023 by iceychris Contributor Loading…
6 tasks done
16
ProTip! Add no:assignee to see everything that’s not assigned.