ascend-910b

Here are 4 public repositories matching this topic...

JohnScheuer / hybrid-inference-runtime

Disaggregated Prefill-Decode serving engine connecting NVIDIA Blackwell (SM120) and Huawei Ascend 910B2 (CANN) across physical nodes.

cuda cann inference-engine heterogeneous-computing kv-cache vllm llm-inference pagedattention deepseek ai-infrastructure distributed-inference nvidia-blackwell disaggregated-serving huawei-ascend ascend-910b pytorch-npu davinci-architecture

Updated Sep 24, 2026
Python

So-cean / mamba-ascendc

Star

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.

pytorch ssd mamba cann performance-optimization state-space-models ascend-npu selective-scan ai-infrastructure ascendc kernel-optimization mamba2 huawei-ascend torch-npu custom-operator ascend-910b triton-ascend ascend-950

Updated Aug 12, 2026
Python

thjyy / ascend-qwen38-27b-field-guide

Star

两张昇腾910B2C部署Qwen3.8-27B W8A8：128K上下文、多模态、工具调用与vLLM-Ascend实战

docker multimodal modelscope vllm llm-inference ascend-npu qwen speculative-decoding tool-calling qwen3 ascend-910b vllm-ascend

Updated Sep 8, 2026

thjyy / ascend-deepseek-v4-field-guide

Star

16卡昇腾910B2C部署DeepSeek-V4-Flash：512K上下文、DSpark、vLLM-Ascend性能调优与故障排查实战

docker-compose performance-tuning vllm llm-inference ascend-npu speculative-decoding deepseek ai-infrastructure deepseek-v4 ascend-910b vllm-ascend dspark

Updated Sep 6, 2026
Shell

Add this topic to your repo

To associate your repository with the ascend-910b topic, visit your repo's landing page and select "manage topics."

Learn more