issues Search Results · repo:pytorch/torchchat language:Python
Filter by
366 results
(155 ms)366 results
inpytorch/torchchat (press backspace or delete to remove)As of May 19th 2025, we are halting active development on torchchat.
The original intent of torchchat was to both demonstrate how to run LLM inference using PyTorch and improve the
performance and functionality ...
Jack-Khuu
- 3
- Opened on May 20
- #1543
🚀 The feature, motivation and pitch
As a sequel to https://github.com/pytorch/torchchat/issues/1518 where we added an enum for tokenizer types to simplify
TokenizerArgs __post_init__, we need to further ...
actionable
good first issue
triaged
zhenyan-zhang-meta
- 3
- Opened on Apr 28
- #1536
🚀 The feature, motivation and pitch
Quantization is a technique used to reduce the speed, size, or memory requirements of a model and torchao is PyTorch s
native quantization library for inference and ...
Quantization
triaged
- 6
- Opened on Mar 31
- #1520
🚀 The feature, motivation and pitch
We would like to make torchtune an optional dependency. The first step towards that is to avoid importing torchtune
unless it is actively used.
To make this migration ...
actionable
good first issue
torchtune
triaged
- 2
- Opened on Mar 31
- #1519
🚀 The feature, motivation and pitch
TokenizerArgs.__post_init__ has grown quite verbose/redundant and could use a bit of simplification
https://github.com/pytorch/torchchat/blob/1384f7d3d7af0847d8364fe7b300a8b49f2213c2/torchchat/cli/builder.py#L244-L289 ...
actionable
good first issue
triaged
- 9
- Opened on Mar 31
- #1518
🐛 Describe the bug
I just follow the tutorial to export an mobile model: python3 torchchat.py export llama3.1 --quantize
torchchat/quant_config/mobile.json --output-pte-path llama3.1.pte
in the torchchat ...
ExecuTorch
Quantization
triaged
TheBetterSolution
- 4
- Opened on Feb 27
- #1506
🚀 The feature, motivation and pitch
PT is deprecating CUDA 12.4 nightly builds: https://github.com/pytorch/test-infra/pull/6333
This repo will need to update CI and testing in response to this
Alternatives ...
CI Infra
Cuda
triaged
- 2
- Opened on Feb 25
- #1504
🚀 The feature, motivation and pitch
Need work to enable:
python3 torchchat.py export llama3.2-11B --output-aoti-package-path exportedModels/llama3_2_artifacts.pt2
Features to be added:
- Run AOTI ...
Compile / AOTI
enhancement
triaged
larryliu0820
- 1
- Opened on Feb 21
- #1497
I see current torchchat serving provides basic serving function. I m wondering what the future plan for serving. What s
the target of torchchat serve? Will it provide more optimized and high performance ...
enhancement
triaged
jenniew
- 3
- Opened on Feb 8
- #1491
🚀 The feature, motivation and pitch
After an ExecuTorch model is exported to a pte, tokenization information must be passed in as an arg (-l # ) to the
runner. This can be avoided by writing this information ...
actionable
enhancement
ExecuTorch
good first issue
triaged
- Opened on Jan 30
- #1484
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.