ForgeKernel from ModelBest ranks #1 on CANNBench and FlashInfer-Bench
A single kernel-generation system topping benchmarks on both Huawei Ascend-class chips and NVIDIA hardware signals that AI-written kernels can reduce vendor lock-in for low-level GPU/NPU optimization. Teams porting models across chip ecosystems — including Huawei's — can use such systems to cut manual kernel engineering time.
ModelBest's ForgeKernel, an AI kernel generation system, ranks #1 on Huawei CANNBench, which covers the 950DT, 950PR and A3 chips, and on NVIDIA SOL-ExecBench (FlashInfer-Bench). The result places one kernel optimization system at the top of both Huawei and NVIDIA hardware ecosystems. ModelBest says ForgeKernel helps bring high-quality kernels to new hardware faster.
🏆 ForgeKernel, our AI kernel generation system, ranks #1 on Huawei CANNBench (950DT, 950PR, A3) and NVIDIA SOL-ExecBench (FlashInfer-Bench). ⚙️ One kernel optimization system, two hardware ecosystems. ForgeKernel helps bring high-quality kernels to new hardware faster. https://t.co/CBWlju27pp
