wbigat/xllm
A high-performance inference engine for LLMs, optimized for diverse AI accelerators.
Repositories
wbigat/pypto
A community-driven pypto implementation
wbigat/claude-code
An independent Python feature port of Claude Code, entirely rewritting from scratch using oh-my-codex. Educational Purpose only.
wbigat/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
wbigat/LongCat-Flash-Thinking-2601
wbigat/Engram
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
wbigat/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
wbigat/torchtitan
A PyTorch native platform for training generative AI models
wbigat/executorch
On-device AI across mobile, embedded and edge for PyTorch
wbigat/vllm-ascend
Community maintained hardware plugin for vLLM on Ascend
wbigat/xpu_graph
A torch compile backend for multi-targets
wbigat/Megatron-LM
Ongoing research training transformer models at scale