Skip to content

Pull requests: qualcomm/GenieX

New pull request New
9 Open 931 Closed
9 Open 931 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

test(sdk): cover text-only VLM prompt tokenization
#1292 opened Aug 5, 2026 by MAN$I VERMA (mansiverma897993) Contributor • Draft
1
fix(sdk): reacquire HTP sessions on all devices, not just NPU
#1289 opened Aug 5, 2026 by Mengsheng Wu (mengshengwu) Contributor Loading…
3 tasks done
@mengshengwu
feat(sdk): add InternVL 3.5 QAIRT model support
#1285 opened Aug 4, 2026 by David Qian (Davidqian123) Contributor Loading…
7 tasks done
1
fix(sdk): patch llama.cpp OpenCL cpy kernel for Adreno
#1284 opened Aug 4, 2026 by RemiliaForever (RemiliaForever) Contributor • Draft
1
ci(release): make release SDK builds hermetic (skip cross-run caches)
#1267 opened Jul 31, 2026 by Nathan Lu (NathanL15) Loading…
feat(cli): add geniex eval - compare models on eval packs
#1260 opened Jul 31, 2026 by MAN$I VERMA (mansiverma897993) Contributor Loading…
1
2
fix(qairt): name recognized dsp_arch values when device creation fails
#1259 opened Jul 31, 2026 by MAN$I VERMA (mansiverma897993) Contributor Loading…
1
1
fix(server): send spec-compliant finish_reason on stream chunks
#1246 opened Jul 28, 2026 by MAN$I VERMA (mansiverma897993) Contributor Loading…
1
5
fix(sdk): enable thinking mode on the llama.cpp VLM path
#1161 opened Jul 8, 2026 by Paul Zhu (vinovo) Contributor • Draft
3 tasks done
ProTip! Adding no:label will show everything without a label.