Skip to content

Issues: pytorch/torchchat

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
21 Open 40 Closed
21 Open 40 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Enable torchao.experimental EmbeddingQuantization Quantization Issues related to Quantization or torchao triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1520 opened Mar 31, 2025 by Jack-Khuu
@dillondesilva
6
torchtune as an optional dependency: Lazy Import actionable Items in the backlog waiting for an appropriate impl/fix good first issue Good for newcomers torchtune Issue/PR related to torchtune components triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1519 opened Mar 31, 2025 by Jack-Khuu
1
Llama3.2 vision model AOTI integration Compile / AOTI Issues related to AOT Inductor and torch compile enhancement New feature or request triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1497 opened Feb 21, 2025 by larryliu0820
1
What's the future plan for torchchat serving enhancement New feature or request triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1491 opened Feb 8, 2025 by jenniew
@Jack-Khuu
3
We still don't use BFDOT on macOS CPU because Apple compiler used for PyTorch wheel is outdated Known Gaps These are known Gaps/Issues/Bug items in torchchat MPS/Metal Issues related to Metal MPS/env set up performance triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1444 opened Dec 27, 2024 by swolchok
2
[KNOWN BUG] Broken Support for TextOnly Models from torchtune bug Something isn't working Known Gaps These are known Gaps/Issues/Bug items in torchchat torchtune Issue/PR related to torchtune components triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1430 opened Dec 19, 2024 by Jack-Khuu
Misaligned AOTI input; potential perf gains by fixing? actionable Items in the backlog waiting for an appropriate impl/fix bug Something isn't working Compile / AOTI Issues related to AOT Inductor and torch compile triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1424 opened Dec 14, 2024 by Jack-Khuu
1
Executorch Slows Down after second or third response in Torchchat bug Something isn't working ExecuTorch Issues related to ExecuTorch installation, export, or build. Mobile uses separate tags Mobile - Android Issues Related to the Android Workflow triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1399 opened Dec 4, 2024 by infil00p
@kirklandsign
8
What is the future plan of model expansion? enhancement New feature or request Question Question about the repo as a whole triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1380 opened Nov 15, 2024 by jenniew
@Jack-Khuu
6
OOM Llama 3.2-11B on RTX 4090 bug Something isn't working performance triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1341 opened Nov 2, 2024 by byjlw
1
False Positive on CI tests: test-readme actionable Items in the backlog waiting for an appropriate impl/fix bug Something isn't working CI Infra Issues related to CI infrastructure and setup triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1315 opened Oct 18, 2024 by Jack-Khuu
2
Eval fails on CUDA with AOTI exported model bug Something isn't working Compile / AOTI Issues related to AOT Inductor and torch compile Evaluation/Benchmarking Issues Related to Evaluation and Benchmarking triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1311 opened Oct 17, 2024 by mikekgfb
@Jack-Khuu
5
Llama 3.2 11B Currently Only Supports Single Image enhancement New feature or request Known Gaps These are known Gaps/Issues/Bug items in torchchat Llama 3.2- Multimodal Issues related to Multimodal of Llama3.2 triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1281 opened Oct 8, 2024 by Jack-Khuu
GeneratorArgs.is_torchtune_model is a misnomer actionable Items in the backlog waiting for an appropriate impl/fix good first issue Good for newcomers triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1273 opened Oct 5, 2024 by Jack-Khuu
convert_hf_checkpoint only relies on model_name to resolve TransformerArgs actionable Items in the backlog waiting for an appropriate impl/fix triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1179 opened Sep 23, 2024 by Jack-Khuu
2
Slimming down torchchat: Replace replace_attention_with_custom_sdpa_attention() with ET's implementation enhancement New feature or request ExecuTorch Issues related to ExecuTorch installation, export, or build. Mobile uses separate tags good first issue Good for newcomers triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#1058 opened Aug 23, 2024 by Jack-Khuu
2
Android App Should Crash gracefully when the tokenizer in the aar doesn't match the model actionable Items in the backlog waiting for an appropriate impl/fix ExecuTorch Issues related to ExecuTorch installation, export, or build. Mobile uses separate tags Mobile - Android Issues Related to the Android Workflow triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#978 opened Jul 30, 2024 by Jack-Khuu
1
Improve the scope of Model Evaluation to AOTI and ET enhancement New feature or request Evaluation/Benchmarking Issues Related to Evaluation and Benchmarking Known Gaps These are known Gaps/Issues/Bug items in torchchat triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#938 opened Jul 22, 2024 by Jack-Khuu
[TORCHAO] Handle non-multiple group sizes, support padding as appropriate in torchao and kernels triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#522 opened Apr 27, 2024 by mikekgfb
@digantdesai @supriyar
@jisaacso @jerryzh168
2
[FEATURE REQUEST] Clang vectoriation on ARM: warning: loop not vectorized triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#521 opened Apr 27, 2024 by mikekgfb
@nadavrot @helloguo
7
[FEATURE REQUEST] connect browser to native (Python-free) execution environment enhancement New feature or request triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#513 opened Apr 27, 2024 by mikekgfb
ProTip! Adding no:label will show everything without a label.