Skip to content

Pull requests: ServiceNow/Fast-LLM

New pull request New
18 Open 307 Closed
18 Open 307 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Sample full layouts instead of independent per layer mixer sampling
#472 opened Mar 6, 2026 by oleksost Loading…
1 of 25 tasks
[Prototype] Improved model preprocessing, new batch structure
#471 opened Feb 17, 2026 by jlamypoirier • Draft
Simplify MTP
#470 opened Feb 11, 2026 by jlamypoirier Loading…
Merge the batch and sequence dimensions
#469 opened Feb 11, 2026 by jlamypoirier Loading…
Triton losses
#466 opened Jan 31, 2026 by jlamypoirier Loading…
1
Entropy loss tweaks
#465 opened Jan 29, 2026 by jlamypoirier Loading…
[EXTERNAL] Add vLLM Apriel2 model with plugin-based registration
#447 opened Jan 12, 2026 by tscholak Loading…
5 of 6 tasks
35
[WIP] Changes for generate and lm_eval after code refactoring
#438 opened Jan 6, 2026 by bigximik • Draft
25 tasks
Add IS evaluator
#432 opened Dec 21, 2025 by tscholak • Draft
[Pipeline RL] Add support for PipelineRL
#428 opened Dec 17, 2025 by jlamypoirier • Draft
10
[Prototype] Normalising by valid tokens
#426 opened Dec 16, 2025 by oleksost • Draft
3 of 25 tasks
4
[hybrid_dev] Cleanup modeling file for Apriel-H
#379 opened Oct 16, 2025 by nitsanluke • Draft
1
[Prototype] Add scalable sparse map kernel for large MoE models (128+ experts)
#375 opened Oct 12, 2025 by tscholak • Draft
3
[Prototype] Add GPT-OSS converter with heterogeneous block pattern support
#374 opened Oct 12, 2025 by tscholak • Draft
11
[Prototype] Concatenated weights and linear layers
#366 opened Sep 22, 2025 by jlamypoirier • Draft
[hybrid_dev] Nemotron-H mamba2
#355 opened Aug 21, 2025 by oleksost • Draft
2 of 26 tasks
3
[hybrid_dev] Hybrid dev branch
#347 opened Aug 7, 2025 by RaymondLi0 • Draft
[Prototype] Masked Diffusion Training with Shift
#294 opened Jun 10, 2025 by nitsanluke • Draft
1 of 25 tasks
ProTip! Exclude everything labeled bug with -label:bug.