Skip to content

Pull requests: ModelCloud/GPTQModel

New pull request New
13 Open 1,422 Closed
13 Open 1,422 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

Add Group Aware Reordering (GAR) for Efficient Activation Reordering
#1656 opened Jul 10, 2025 by tgafni Loading…
[KERNEL] machete
#1597 opened May 7, 2025 by LRL-ModelCloud • Draft
Mistral3 Support
#1563 opened Apr 29, 2025 by Qubitium • Draft
1
Fix v2 for MoE
#1548 opened Apr 17, 2025 by Qubitium • Draft
Google TPU Support
#1532 opened Apr 10, 2025 by Qubitium Loading…
Llama 4 Support
#1508 opened Apr 6, 2025 by Qubitium • Draft
2
add faster packing
#1464 opened Mar 14, 2025 by Qubitium • Draft
WIP: compile foward
#1276 opened Feb 13, 2025 by CSY-ModelCloud • Draft
tokenicer.save()
#1270 opened Feb 12, 2025 by CL-ModelCloud Loading…
reduce memory
#1195 opened Feb 1, 2025 by Qubitium • Draft
use second gpu for add_batch and self.H sum
#1194 opened Feb 1, 2025 by Qubitium • Draft
[MODEL] support minicpm-o 2.6
#1116 opened Jan 20, 2025 by ZX-ModelCloud Loading…
[MODEL] Intern vl2 support
#970 opened Dec 25, 2024 by ZX-ModelCloud • Draft
1
ProTip! Mix and match filters to narrow down what you’re looking for.