#
vllm-ascend
Here are 4 public repositories matching this topic...
AST-only compatibility analyzer for vLLM to vllm-ascend main2main upgrades: patches, overrides, imports, calls, Triton launches, signatures, and return protocols.
-
Updated
Aug 19, 2026 - Python
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
Deploy GLM-4.6V-Flash (9B dense VLM) on Huawei Ascend 910B NPU with vLLM - multimodal, OpenAI API, single/dual-card serving, reproducible benchmarks.
-
Updated
Jun 9, 2026 - HTML
Add this topic to your repo
To associate your repository with the vllm-ascend topic, visit your repo's landing page and select "manage topics."