Popular repositories Loading

1. Lvllm Lvllm Public

   LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features an efficient GPU parallel and NUMA parallel architecture, su…

   Python 388 35

2. Lsglang Lsglang Public

   Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parallel architecture, suitable for MOE model hybrid inference.

   Python 101 9

3. lktransformers lktransformers Public archive

   The complete NUMA-optimized branch of the ktransformers project

   Python 25 10

4. Lvllmds4 Lvllmds4 Public

   A fork of jasl/vllm (codex/ds4-sm120-min-enable) with CPU-GPU hybrid inference support for DeepSeek-V4 on SM120+.

   Python 13 1

5. Lvllmds4-x Lvllmds4-x Public

   CPU-GPU hybrid inference for DeepSeek-V4 on NVIDIA SM80+ (A100/RTX 4090 etc.), forked from yhfgyyf/vllm-deepseek-v4-sm89.

   Python 8