Skip to content
Tagged articles

Static Kernel

1 articles · Page 1 of 1
DeWu Technology
DeWu Technology
Oct 21, 2026 · Artificial Intelligence

Ascend 910C LLM Inference Optimization: Image & Parameter Tuning for 40% Speedup

Dewu Technology details how they optimized Qwen3.5-35B-A3B inference on Huawei Ascend 910C NPU, cutting TPOT 45% via vLLM-Ascend 0.23.0 upgrade, HCCL offload to AIVector, static kernel precompilation, HBM allocator tuning, jemalloc, operator caching, MoE weight prefetch, HCCL parameters, and cudagraph config, while documenting over ten failed attempts.

Ascend 910CCUDAGraphHCCL
0 likes · 26 min read
Ascend 910C LLM Inference Optimization: Image & Parameter Tuning for 40% Speedup