Popular repositories Loading

1. OpenNeedle OpenNeedle Public

   Open-source CPU inference and PyTorch tools for Needle 2: CQ2/CQ4 quantization, model conversion, QAT, and ARM NEON/SDOT kernels.

   Python 2

2. LLM-EdgeFlow LLM-EdgeFlow Public

   High-performance C++ pipeline & heterogeneous inference framework for Edge AI & LLMs, featuring fixed-batch DMA scheduling, multi-modal DAG orchestration, and pure C ABI isolation.

   C++ 1

3. NPU-Micro-Translator NPU-Micro-Translator Public

   A ~100M parameter Qwen3-based multilingual-to-Chinese machine translation model, trained from scratch with an automated AutoResearch pipeline.

   Python

4. llm-vocab-pruner llm-vocab-pruner Public

   Extensible output-vocabulary pruning for decoder-only LLMs while preserving multilingual input embeddings. Tested on Qwen2/Qwen2.5 and Gemma 3.

   Python

5. TranslateEval TranslateEval Public

   A multilingual-to-Chinese translation evaluation platform with LLM-based scoring, model comparison, and evaluation tracking.

   Python