IntelliStream
Official@intellistream · China
Research group focused on stream processing, AI systems, and intelligent databases.
Agent Skills by IntelliStream
Showing 3 vetted skills indexed across 1 GitHub repositories.
vLLM Ascend Release Note Writer
Generate structured vLLM Ascend release notes from commits between two tags.
main2main
Guide adaptation of vLLM main branch code for the Ascend project.
vllm-ascend-model-adapter
Adapt Hugging Face/local ML models for vLLM Ascend hardware with validated, signed commits and documentation.
Frequently Asked Questions About IntelliStream
FAQPage SchemaWhat specific tasks does IntelliStream enable for hardware engineers?▼
IntelliStream enables the systematic porting of vLLM inference frameworks to Ascend hardware. It facilitates the adaptation of model architectures, ensures version consistency between main branch code and hardware-specific forks, and generates structured release documentation based on commit history between repository tags.
Which technical personas benefit from these capabilities?▼
These capabilities are designed for machine learning engineers, hardware integration specialists, and infrastructure developers working on high-performance inference deployments. It is specifically intended for teams managing the lifecycle of vLLM-based services running on Ascend NPU hardware.
What are the prerequisites for using these model adaptation skills?▼
Users require an existing vLLM codebase, access to Ascend hardware environments, and a repository structure utilizing Git tags for versioning. The adaptation process assumes familiarity with Hugging Face model formats and the specific architectural requirements of the Ascend compute stack.