bertholomus/spark-attic
More memory for CUDA on an NVIDIA GB10 (DGX Spark, ASUS Ascent GX10): lend the unused display carveout to vLLM, SGLang and TensorFold as KV cache
GitHub repository with 9 stars and 0 forks.
Language: Python
Topics: cuda, dgx-spark, gb10, kv-cache, sglang, tensorfold, vllm