Qwen3-8B **PD 分离**(`pd_master` + `prefill` + `decode`)本地 GSM8K 评测
Facilitates testing and evaluation of the Qwen3-8B model using NIXL architecture with GPU management and logging capabilities.
5,493,675 AI resources indexedWorking toward the world’s largest AI resource index.
Reusable instructions for compatible AI agents.
Field counts come from the latest full-catalog snapshot. A resource can belong to several fields and platforms.
Facilitates testing and evaluation of the Qwen3-8B model using NIXL architecture with GPU management and logging capabilities.
Facilitates running and logging of LightLLM DeepSeek-R1 EP MoE + MTP server variants for accuracy evaluation workflows.
Facilitates tensor parallel testing for DeepSeek-R1 models using LightLLM API, optimizing GSM8K evaluations on localhost.
Try a broader search or clear some filters.
Platform labels describe intended use. Read each resource's author credits, requirements and available access methods.