Verified record · from the answer index

benchmark-vllm-model

Benchmark throughput and cost-per-token of a model served on vLLM in Chalk's container infrastructure. Use when someone asks for $/token, $/request, tokens/sec, "how much would it cost to self-host this model", GPU sizing for an LLM, or wan

skill:chalk-ai/chalk-ai-plugins/benchmark-vllm-model · published by chalk-ai · source repository