Pinned Loading

1. sparkinfer sparkinfer Public

   Forked from local-inference-lab/sparkinfer

   Python

2. vllm vllm Public

   Forked from local-inference-lab/vllm

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python

3. inference-runtime-profiles inference-runtime-profiles Public

   Portable, privacy-safe runtime profiles for reproducible GPU inference deployments

   Python 2

4. vllm-observer vllm-observer Public

   Drop-in, read-only observability dashboard for vLLM workloads

   Python

5. sparkring sparkring Public

   Serving GLM-5.2 on four directly-cabled DGX Sparks: switchless 200GbE ring, custom RDMA collectives, CUDA-graph transport, patched NCCL, SparkCache persistent KV cache

   Python 4

6. glm52-v17-lmcache-ckv-gather glm52-v17-lmcache-ckv-gather Public

   Experimental GLM-5.2 v17 TP4/DCP4 image with RAM LMCache and CKV-gather prefill optimization

   Python 2