4 Pull requests merged by 3 people

• Bump torchao pin to pick up qmv_fast optimization

  #1541 merged May 13, 2025

• Push torchtune install deeper in generate._gen_model_input and undo import order change for etmodel

  #1542 merged May 12, 2025

• Move imports to prepare for making torchtune an optional dependency

  #1539 merged May 12, 2025

• Bumping ET Pin to pick up PT and tune pin updates: May 9th

  #1538 merged May 12, 2025

1 Pull request opened by 1 person

• Unified tokenizer type onboarding

  #1540 opened May 11, 2025

5 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Enabling EmbeddingQuantizer and SharedEmbeddingQuantizer

  #1525 commented on May 13, 2025 • 5 new comments

• Llama 3.2 11B Currently Only Supports Single Image

  #1281 commented on May 11, 2025 • 0 new comments

• Improve Tokenizer New Type Onboarding

  #1536 commented on May 13, 2025 • 0 new comments

• GeneratorArgs.is_torchtune_model is a misnomer

  #1273 commented on May 16, 2025 • 0 new comments

• Add benchmarking scripts

  #1030 commented on May 16, 2025 • 0 new comments