Popular repositories Loading
-
dgx-spark-nvfp4-serving
dgx-spark-nvfp4-serving PublicGuide for serving fine-tuned Qwen3.5-27B (dense, NVFP4) on DGX Spark via native vLLM. Includes critical config fixes for modelopt export_hf_checkpoint() that prevent silent FP32 dequantization.
Python 2
-
design-challenger
design-challenger PublicAdversarial design review agent — spawns writer + challenger Claude Code agents to stress-test specs and implementation plans for any codebase
TypeScript
-
vllm
vllm PublicForked from vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Python
-
mac-studio-mlx-serving
mac-studio-mlx-serving PublicBenchmarks and serving notes for Qwen3.5-27B fine-tune on Apple Silicon via MLX. Companion to dgx-spark-nvfp4-serving.
Python
If the problem persists, check the GitHub status page or contact support.