Skip to content

Pull requests: apple/axlearn

New pull request New
39 Open 1,056 Closed
39 Open 1,056 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

Differentiate SUCCEED and FAILED at the end of the Flink-Beam job
#1150 opened May 2, 2025 by jinglu1 Loading…
Convert timestamp to datetime.
#1148 opened May 1, 2025 by markblee Loading…
Save O_PROJ on Fuji 70B-v2 for TRN2
#1147 opened May 1, 2025 by apoorvtintin Loading…
Fallback to standard mesh on neuron backend for incompatible multi-granule meshes
#1146 opened May 1, 2025 by apoorvtintin Loading…
Page Attention GPU Kernel Integration
#1137 opened Apr 28, 2025 by christ-tt Loading…
1
[Jax API update] Remove jax_spmd_mode
#1136 opened Apr 28, 2025 by Steboss Loading…
25
Makes logic in optimizers use 1-based steps.
#1118 opened Apr 19, 2025 by ruomingp • Draft
repro PR for test_spmd_evaler fail with jax 0.5.3
#1114 opened Apr 18, 2025 by matthew-e-hopkins • Draft
Add ROCm support
#1112 opened Apr 16, 2025 by akasharidas Loading…
14
Migrate from Legacy JAX APIs jax.tree_util to jax.tree
#986 opened Feb 12, 2025 by apivovarov Loading…
7
Use Accuracy from cross_entropy in causal_lm.py::CrossEntropyLossMetrics
#983 opened Feb 12, 2025 by apivovarov Loading…
3
Adds logging to aux loss collection.
#950 opened Jan 26, 2025 by ruomingp Loading…
1
Uses pytest markers instead of module skip.
#941 opened Jan 22, 2025 by markblee • Draft
use "true" and "false" instead of 0 and 1
#890 opened Dec 12, 2024 by samos123 Loading…
14
restore test_apply_paddings_check runtime_checks test
#771 opened Oct 22, 2024 by mattjj Loading…
5
add Fuji v3 405b and solve HBM OOMs for larger models
#766 opened Oct 21, 2024 by samos123 • Draft
17
Alternative method of submitting jobs to DF Runner
#756 opened Oct 17, 2024 by remylouisew Loading…
4
Converts checkpointer and state builder to configurable.
#751 opened Oct 14, 2024 by markblee • Draft
Use regex for parsing step_dir
#739 opened Oct 7, 2024 by nlusskin Loading…
5
Set TF_FORCE_GPU_ALLOW_GROWTH=true by default
#712 opened Sep 24, 2024 by samos123 Loading…
2
Fix submission of Dataflow jobs
#711 opened Sep 24, 2024 by damccorm Loading…
2
ssm_enhancement
#689 opened Sep 6, 2024 by vishesh9131 • Draft
12
Makes BoundedAsyncCheckpointManager control max_concurrent_gb by the size of local shards instead of global shards.
#649 opened Aug 12, 2024 by ruomingp • Draft
Add @no_side_effects.
#647 opened Aug 9, 2024 by apghml Loading…
2
set hostNetwork to True for TPUGKEJob
#641 opened Aug 8, 2024 by samos123 Loading…
5
ProTip! Filter pull requests by the default branch with base:main.