Skip to content

Pull requests: ericcurtin/inferrs

New pull request New
6 Open 214 Closed
6 Open 214 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

feat: add support for loading local GGUF models
#247 opened May 7, 2026 by zzzdong Loading…
5
feat(ui): split assets, expose stats/controls, surface model metadata
#246 opened May 1, 2026 by igorls Contributor Loading…
14 tasks done
9
fix(gemma4): GGUF MoE loading, OOM-safe expert split, tolerant quant config
#245 opened Apr 30, 2026 by igorls Contributor Loading…
4 tasks
6
fix(config): lenient deserialization of quantization_config
#242 opened Apr 30, 2026 by igorls Contributor Loading…
1
6
feat: speculative decoding with external draft model
#221 opened Apr 17, 2026 by jexp Contributor • Draft
1
9
Optimize Gemma-4 decode: fused Metal kernels, model-specific quant recipes
#210 opened Apr 15, 2026 by ericcurtin Owner Loading…
7
ProTip! Follow long discussions with comments:>50.