LMCache multiprocess (MP) mode — standalone LMCache server in its own pod/process that vLLM connects to over ZMQ. Provides process isolation, no GIL contention on the inference path, one cache shared by multiple vLLM pods on the same node, and CPU-memory scaling independent of GPU memory. Covers the LMCacheMPConnector path (the new direction; LMCacheConnectorV1 in-process path still works but is being upstaged), DaemonSet+Deployment K8s pattern, L1 (CPU DRAM) + L2 (NIXL POSIX / GDS / HF3FS, plain fs, mooncakestore, s3) cascade, the lmcache/standalone:nightly + lmcache/vllm-openai:latest-nightly image pair vs stock vllm/vllm-openai, and the production gotchas (--no-enable-prefix-caching on vLLM side, --disable-hybrid-kv-cache-manager required, vLLM/lmcache version compatibility, hybrid-model NOT supported yet, cachesalt fallback adapter bug).
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryEngineeringStars0
About this skill
LMCache multiprocess (MP) mode — standalone LMCache server in its own pod/process that vLLM connects to over ZMQ. Provides process isolation, no GIL contention on the inference path, one cache shared by multiple vLLM pods on the same node, and CPU-memory scaling independent of GPU memory. Covers the LMCacheMPConnector path (the new direction; LMCacheConnectorV1 in-process path still works but is being upstaged), DaemonSet+Deployment K8s pattern, L1 (CPU DRAM) + L2 (NIXL POSIX / GDS / HF3FS, plain fs, mooncakestore, s3) cascade, the lmcache/standalone:nightly + lmcache/vllm-openai:latest-nightly image pair vs stock vllm/vllm-openai, and the production gotchas (--no-enable-prefix-caching on vLLM side, --disable-hybrid-kv-cache-manager required, vLLM/lmcache version compatibility, hybrid-model NOT supported yet, cachesalt fallback adapter bug).
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
LMCache multiprocess (MP) mode — standalone LMCache server in its own pod/process that vLLM connects to over ZMQ. Provides process isolation, no GIL contention on the inference path, one cache shared by multiple vLLM pods on the same node, and CPU-memory scaling independent of GPU memory. Covers the `LMCacheMPConnector` path (the new direction; `LMCacheConnectorV1` in-process path still works but is being upstaged), DaemonSet+Deployment K8s pattern, L1 (CPU DRAM) + L2 (NIXL POSIX / GDS / HF3FS, plain fs, mooncake_store, s3) cascade, the `lmcache/standalone:nightly` + `lmcache/vllm-openai:latest-nightly` image pair vs stock `vllm/vllm-openai`, and the production gotchas (--no-enable-prefix-caching on vLLM side, --disable-hybrid-kv-cache-manager required, vLLM/lmcache version compatibility, hybrid-model NOT supported yet, cache_salt fallback adapter bug).
About this listing
Category
Engineering
Reported license
Not specified
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI