Popular repositories Loading

1. ascend310p-llm ascend310p-llm Public

   LLM inference adaptation for Ascend 310P (Atlas 300I DUO): Qwen3.6 W4A8/MTP/C8 and Qwen3.8 TP2, with reproducible results

   Python

2. engineering-notes engineering-notes Public

   真实工程问题的排查与设计记录：AI Infra、网络、推理服务与 Agent 工程

   Astro

3. consumer-gpu-llm consumer-gpu-llm Public

   Qwen3.8-27B-FP8 serving on 4x RTX 4090 48G with vLLM: tuning scripts, raw benchmark data and write-ups

   Shell

4. vllm-ascend vllm-ascend Public

   Forked from vllm-project/vllm-ascend

   Community maintained hardware plugin for vLLM on Huawei Ascend

   Python

5. sub2api sub2api Public

   Forked from Wei-Shaw/sub2api

   Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

   Go

6. WeKnora WeKnora Public

   Forked from Tencent/WeKnora

   Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

   Go