-
Notifications
You must be signed in to change notification settings - Fork 223
Pull requests: nunchaku-ai/nunchaku
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(lora): implement fast LoRA switching for instant variant switching
#897
opened Jan 29, 2026 by
sqhuang
Loading…
4 tasks done
[Qwen] Validate encoder_hidden_states for text sequence length
#887
opened Jan 19, 2026 by
kashif
Loading…
6 tasks
feat(zimage): add LoRA support for NunchakuZImageTransformer2DModel
#866
opened Jan 5, 2026 by
sqhuang
Loading…
feat: Enable deterministic LoRA activation reduction using fixed-point arithmetic
#820
opened Dec 17, 2025 by
lantudou
Loading…
Performance fix: add pin_memory option (default on for CUDA) to speed…
#817
opened Dec 12, 2025 by
tonera
Loading…
Add diverse examples for Cache-dit in Flux.1 and Qwen models regarding #763
#810
opened Nov 26, 2025 by
Bluear7878
Loading…
feat: NunchakuFluxTransformer2DModelV2 supports lora
#792
opened Oct 31, 2025 by
devgdovg
Loading…
4 of 6 tasks
feat: Add LoRA and ControlNet support for Qwen Image models
#754
opened Oct 10, 2025 by
black4der
Loading…
16 tasks done
feat: Python Backend Float16 Support for Turing GPUs
#686
opened Sep 12, 2025 by
Bluear7878
Loading…
Remove unexpected code in compose_lora to resolve bugs
#566
opened Jul 25, 2025 by
iceload123
Loading…
6 tasks
fix: fix the LoRA loading issue in #265
#384
opened May 21, 2025 by
StarMingGao
Loading…
1 of 6 tasks
Add cog.yaml and predict.py for usage with Replicate and Docker
#39
opened Dec 1, 2024 by
voodoohop
Loading…
ProTip!
Follow long discussions with comments:>50.