Skip to content

Pull requests: pytorch/benchmark

New pull request New
72 Open 1,610 Closed
72 Open 1,610 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Improve log message when a test is skipped due to metadata. cla signed
#2611 opened Apr 24, 2025 by DanaBCooper Loading…
deprecate gym to gymnasium and add timm yaml file back cla signed
#2609 opened Apr 10, 2025 by Camyll Loading…
Support activation quantization cla signed fb-exported
#2607 opened Apr 9, 2025 by mengluy0125 Loading…
9
Upgrade to cuda 12.8 in the base docker cla signed
#2605 opened Apr 2, 2025 by xuzhao9 Loading…
1
adding file timm_models.yaml cla signed
#2603 opened Mar 28, 2025 by xuanzhang816 • Draft
[Fix Syn] add missing yaml file manually cla signed
#2602 opened Mar 18, 2025 by yangw-dev Loading…
1
Fix: Ensure install_diffusers() is called before HUGGING FACE token check cla signed
#2599 opened Mar 10, 2025 by AdrianTamasDev Loading…
Initial setup for export benchmarking suite and some models cla signed
#2596 opened Mar 6, 2025 by tugsbayasgalan Loading…
1
Enable PT2E quantization for CPU cla signed
#2594 opened Feb 21, 2025 by zxd1997066 Loading…
1
[Userbenchmark] Add configuration support for test_bench cla signed
#2592 opened Feb 12, 2025 by shink Loading…
1
3
Bump transformers from 4.44.2 to 4.48.0 cla signed dependencies Pull requests that update a dependency file
#2591 opened Feb 11, 2025 by dependabot bot Loading…
Changing llama_v2_70b to correct config class cla signed
#2588 opened Feb 7, 2025 by JasonMts Loading…
3
Let model precision for XPU device align with CUDA cla signed
#2587 opened Feb 6, 2025 by jianyizh Loading…
9
Apply changes to userbenchmark a100 release cla signed
#2586 opened Feb 4, 2025 by atalman Loading…
Cast inputs type to dictionary. cla signed
#2585 opened Jan 30, 2025 by ostrowskimarcin Loading…
2
Small fix on how to get GPU memory for CUDA devices cla signed
#2582 opened Jan 27, 2025 by jeanschmidt Loading…
1
Add requirements files for models cla signed
#2580 opened Jan 27, 2025 by JasonMts Loading…
3
Deleting recursion loop for fambench_xlmr cla signed
#2579 opened Jan 27, 2025 by JasonMts Loading…
3
Make test py run test inductor cla signed
#2578 opened Jan 27, 2025 by gbeckenkamp Loading…
Add quantized back cla signed
#2577 opened Jan 27, 2025 by gbeckenkamp Loading…
3
[not4land] Local torchao benchmark cla signed
#2562 opened Jan 5, 2025 by jerryzh168 Loading…
Add option to support garbage collection after torch compilation cla signed fb-exported
#2559 opened Dec 13, 2024 by qiurc Loading…
6
Enable autoquant for CPU userbenchmark cla signed
#2547 opened Nov 25, 2024 by zxd1997066 • Draft
3
Add --device_only arg to test_bench.py cla signed
#2542 opened Nov 19, 2024 by shink Loading…
1
Update userbenchmark-a100-release.yml use linux.aws.a100 cla signed
#2540 opened Nov 18, 2024 by atalman Loading…
ProTip! What’s not been updated in a month: updated:<2025-03-25.