LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
Free
1 MCP server
Data Science & MLWorks with PerplexityBy stevecrates489-commits
Scanned where there is a package or repository to read, and every release diffed against the tool surface we already hold.
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.