Skip to content

Pull requests: ServiceNow/Fast-LLM

New pull request New
17 Open 245 Closed
17 Open 245 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

Fix Qwen converter to correctly load QKV biases
#398 opened Nov 28, 2025 by bigximik • Draft
1 of 8 tasks
2
Apriel 2
#397 opened Nov 27, 2025 by tscholak Loading…
Multimodal hugging Face wrapper, misc improvements, model debugging utils
#396 opened Nov 27, 2025 by jlamypoirier Loading…
Kda mixer
#395 opened Nov 26, 2025 by oleksost Loading…
5 of 26 tasks
GDN mixer
#392 opened Nov 19, 2025 by oleksost Loading…
14 of 31 tasks
1
[hybrid dev] HF GDN and Kimi Linear layers for vllm benchmarking
#390 opened Nov 17, 2025 by oleksost • Draft
1 of 25 tasks
Staging Area for the new datasets implementation and Streaming Dataset Development
#389 opened Nov 17, 2025 by bigximik • Draft
25 tasks
activation-level disillation
#388 opened Nov 14, 2025 by RaymondLi0 • Draft
1 of 19 tasks
1
3
Distributed unit tests, newer transformers and trainer fixes
#387 opened Nov 13, 2025 by bigximik Loading…
1 of 8 tasks
8
[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 Loading…
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 Loading…
2 of 26 tasks
3
[hybrid_dev] Hybrid dev branch
#347 opened Aug 7, 2025 by RaymondLi0 Loading…
[Prototype] Masked Diffusion Training with Shift
#294 opened Jun 10, 2025 by nitsanluke • Draft
1 of 25 tasks
[Prototype] Multimodal Audio
#272 opened May 15, 2025 by tobyzl2 • Draft
25 tasks
1
ProTip! Adding no:label will show everything without a label.