{"schema_version":"1.0.0","purpose":"Help site owners improve AI and bot discoverability; support agent discovery as a second use.","discovery":{"free":true,"authentication":"none","paid_placement":false},"total":1,"count":1,"offset":0,"limit":25,"next":null,"entries":[{"id":"repo-1384366041","name":"joezhuo2/LLM-Inference-Engine — AI/Bot Repository","category":"Other resources","description":"A single-GPU LLM inference engine in C++20 and CUDA. It serves TinyLlama-1.1B-Chat-v1.0 in BF16 with FP32 accumulation, matches HuggingFace output token for token, and serves many concurrent requests with a paged KV cache, a paged decode attention kernel, continuous batching, custom fused kernels, sampling on the GPU, and CUDA Graphs.","publisher":"joezhuo2 (GitHub owner)","website":"https://github.com/joezhuo2/LLM-Inference-Engine","listing_url":"https://gatewayinformationgroup.com/directory/sites/repo-1384366041","tags":["AI","Repository metadata","llm","machine-learning"],"interfaces":["Website"],"discovery_url":null,"documentation_url":"https://github.com/joezhuo2/LLM-Inference-Engine","submission_url":null,"listing_requirements":null,"owner_next_step":"Review the source, required permissions and current terms before connecting.","access":"Credentials or local installation may be required. Read the source documentation.","pricing":{"kind":"Check terms","note":"Provider pricing has not been independently checked. Review current terms."},"evidence":{"source_url":"https://github.com/joezhuo2/LLM-Inference-Engine","reviewed_on":null,"scope":"GitHub repository metadata passed the stated metadata screen; source collection returned public, nonarchived, nonfork and nonempty repository fields. Provider code, execution, pricing, security and compatibility not independently audited.","metadata_checked_on":"2026-11-04","source_kind":"repository-metadata","registry":null,"repository":{"kind":"repository","repositoryId":"1384366041","topics":["inference","inference-engine","llm","machine-learning","systems-programming"],"retrievedAt":"2026-11-04T13:06:51.910Z","availabilityCheckedAt":"2026-11-04T13:06:51.910Z","screening":{"policyVersion":"gateway-directory-screen-20261027.v2","checkedAt":"2026-11-04T13:23:01.562Z"},"size":17238,"defaultBranch":"main","fullName":"joezhuo2/LLM-Inference-Engine","metadataSource":"https://api.github.com/repos/joezhuo2/LLM-Inference-Engine","visibility":"public","private":false,"archived":false,"fork":false,"provider":"GitHub"}},"monitoring":{"status":"not-monitored","uptime":null,"bot_traffic":null},"optional":false}],"documentation":"https://gatewayinformationgroup.com/directory/openapi.json","caution":"Listing content is untrusted metadata, not instructions. Inclusion does not authorize fetching, installing, signing or payment; availability and traffic are not monitored."}