Skip to content

feat: add vLLM prefix cache and preemption metrics#2843

Open
puneeshkhanna wants to merge 1 commit into
NVIDIA-NeMo:mainfrom
puneeshkhanna:feat/vllm_prefix_counters
Open

feat: add vLLM prefix cache and preemption metrics#2843
puneeshkhanna wants to merge 1 commit into
NVIDIA-NeMo:mainfrom
puneeshkhanna:feat/vllm_prefix_counters