Skip to content

Pull requests: lightvector/KataGo

New pull request New
29 Open 234 Closed
29 Open 234 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

[AMD NPU] Add a RyzenAI backend that runs the network on the AMD NPU
#1240 opened Aug 18, 2026 by Looong01 Contributor Loading…
1
CUDA and ROCm optimizations
#1239 opened Aug 18, 2026 by lightvector Owner Loading…
3
Add MIGraphX backend for AMD GPUs (ROCm) — 2.94x over OpenCL on MI300X
#1235 opened Aug 12, 2026 by zhihuidu-amd Loading…
37
Serialize complete TensorRT handle initialization across GPU threads
#1230 opened Aug 6, 2026 by zsqdx Contributor • Draft
Optimize TensorRT CUDA Graph/concurrency and add benchmark auto-tuning
#1219 opened Jul 28, 2026 by zsqdx Contributor • Draft
Add Human-SL even-game ELO rank ladder configs (gtp_human<rank>.cfg, 8d→25k)
#1209 opened Jun 26, 2026 by ChinChangYang Contributor Loading…
5
TensorRT 11 support (Blackwell / strongly-typed networks), incl. FP16
#1206 opened Jun 6, 2026 by gweber Loading…
Tune NN server threads and max batch size in genconfig
#1201 opened May 26, 2026 by zsqdx Contributor • Draft
2
Add MLX backend for Apple Silicon (GPU + ANE/CoreML dispatch, incl. transformer nets)
#1199 opened May 23, 2026 by ChinChangYang Contributor • Draft
1
Configure clang-tidy static analysis in CMake
#1190 opened Apr 25, 2026 by KvanTTT Contributor Loading…
2
Add tune-params subcommand for PUCT hyperparameter tuning via QRS optimization
#1178 opened Apr 1, 2026 by ChinChangYang Contributor Loading…
4 tasks done
[Intel NPU/GPU] Add Windows & Linux Intel NPU & GPU support
#1171 opened Mar 16, 2026 by Looong01 Contributor Loading…
32
Support ONNX models in TensorRT backend
#1139 opened Dec 31, 2025 by hzyhhzy Contributor Loading…
Cuda graph implementation on trt backend
#1071 opened Jun 6, 2025 by zjuwyz Loading…
7
Add human SL value mixing
#1004 opened Dec 3, 2024 by lightvector Owner Loading…
Eval cache
#992 opened Oct 8, 2024 by lightvector Owner Loading…
3
Android support
#978 opened Aug 23, 2024 by jopdorp Loading…
fix b1c6nbt model invalid mid_num_channels setting.
#976 opened Aug 20, 2024 by b05902062 Loading…
1
added web server support for human sl
#970 opened Aug 7, 2024 by jopdorp • Draft
Drastic reduction in trt plan cache size
#946 opened Jun 8, 2024 by hyln9 Contributor Loading…
4
Feat add total visits
#905 opened Feb 29, 2024 by kinfkong Contributor Loading…
Suppress vl visits rebased
#864 opened Dec 16, 2023 by lightvector Owner • Draft
Attempting to cluster correlation outputs using OPTICS
#824 opened Jul 28, 2023 by OmnipotentEntity Contributor Loading…
5
Upgrade to tensorflow 2.4.0
#635 opened May 4, 2022 by Fierralin Loading…
7
add friendlyMaxVisitsFactor setting
#533 opened Jul 29, 2021 by bailsman Loading…
1
ProTip! Add no:assignee to see everything that’s not assigned.