ascendc
Here are 6 public repositories matching this topic...
Native AscendC Mamba2 selective scan / SSD forward-backward custom operator for Huawei Ascend 910B3 and 950PR, with CANN, torch_npu, A100 benchmarks and msprof profiling.
-
Updated
Oct 7, 2026 - Python
High-performance FFT operator library for Huawei Ascend, applying cuButterfly's parameterized hybrid-dataflow method with hardware profiling, performance modeling, and autotuning.
-
Updated
Oct 17, 2026 - Python
鸿蒙端侧 NPU 实战（麒麟 9010）：真实 Qwen 权重在 NPU 上跑通；算子写法差 500 倍（MatMul 549ms → 等价 1x1 Conv 1ms）| HarmonyOS NEXT + HiAI Foundation NPU operators on Kirin 9010
-
Updated
Oct 14, 2026 - Python
An observable multi-agent lab for Ascend kernel engineering: Deep Agents, A2A, independent simulation and curated judging.
-
Updated
Oct 19, 2026 - Python
Ascend NPU linear-attention operator optimization | GDN eager->AscendC on Qwen3.5-0.8B, 3.45x speedup with verified accuracy alignment
-
Updated
Sep 28, 2026 - Python
Add this topic to your repo
To associate your repository with the ascendc topic, visit your repo's landing page and select "manage topics."