Repository navigation

[QEff. Finetuning] Adding TP+DDP support in HF Trainer stack - #907

Closed

smedhe wants to merge 23 commits into

qualcomm:ft_experimental_v1from

smedhe:hf_trainer_tp_ddp

Closed

[QEff. Finetuning] Adding TP+DDP support in HF Trainer stack#907
smedhe wants to merge 23 commits into
qualcomm:ft_experimental_v1from
smedhe:hf_trainer_tp_ddp

Commits on Mar 30, 2026
- [QEff. Finetune]: Added logger and its test cases. (#644) (#868)
  
  smedhe
  authored and
  Ann Kuruvilla (quic-akuruvil)
  committed
  f44e5d0
- [QEff. Finetune_experimental] cherrypicking pr (#870)
  
  smedhe
  authored and
  Ann Kuruvilla (quic-akuruvil)
  committed
  afdab67
- [QEff. finetune_experimnetal] cherry picking PR-787, 791,813,795 (#872)
  
  smedhe
  and
  Ann Kuruvilla (quic-akuruvil)
  committed
  888fbb1
- Formatted docs
  Ann Kuruvilla (quic-akuruvil)
  committed
  14260f9
- [QEff.finetune] Adding style remix dataset config (#858)
  
  Tanisha Chawada (tchawada)
  authored and
  Ann Kuruvilla (quic-akuruvil)
  committed
  3b6558f
- Commented unit test from cloud module
  Ann Kuruvilla (quic-akuruvil)
  committed
  2d6d60b
- Added exception handling for dataset loading
  Ann Kuruvilla (quic-akuruvil)
  committed
  6887919
- Format
  Ann Kuruvilla (quic-akuruvil)
  committed
  fbd1f64
- [QEff. Finetuning]: Tests for Pipeline Parallelism and updated documentation (#893)
  
  Swati Allabadi (quic-swatia)
  authored and
  Ann Kuruvilla (quic-akuruvil)
  committed
  c03e455
- Fixed repolinter error
  Ann Kuruvilla (quic-akuruvil)
  committed
  5d5f0ce
- Corrected file paths
  Ann Kuruvilla (quic-akuruvil)
  committed
  53d6855
- Updates
  Ann Kuruvilla (quic-akuruvil)
  committed
  fb3fb86
- Added Trainer arguments reference
  Ann Kuruvilla (quic-akuruvil)
  committed
  6241bdd
- Addressed some Qgenie reviews and fixed code
  Ann Kuruvilla (quic-akuruvil)
  committed
  d782717
- Added security checks for import_func in dataset.py
  Ann Kuruvilla (quic-akuruvil)
  committed
  a0f0e80
Commits on Mar 31, 2026
- Adding reference data test for finetune (#897)
  Tanisha Chawada (tchawada)
  authored
  a3fefcf
- [QEff. Finetuning]: Updating PP documentation (#899)
  Swati Allabadi (quic-swatia)
  authored
  e9e7a7f
Commits on Apr 6, 2026
- Initial commit: Adding TP+DDP support in hf trainer stack
  smedhe
  committed
  ee92e08
- adding back the AOT stack imports
  smedhe
  committed
  7c9965d
- adding readme and config files for tp+ddp
  smedhe
  committed
  96b71de
Commits on Apr 16, 2026
- adding test cases for tp and ddp, along with other fixes
  smedhe
  committed
  0e02eea
- Adding local world size checks
  smedhe
  committed
  6a73c0f
Commits on Apr 21, 2026
- adding tp+ddp related config changes
  smedhe
  committed
  79541aa

Commits

Commits on Mar 30, 2026

Commits on Mar 31, 2026

Commits on Apr 6, 2026

Commits on Apr 16, 2026

Commits on Apr 21, 2026