genpark-kv-cache-paged-attention-allocator-skill
Enables MCP clients to manage LLM inference memory through virtual paged-attention KV-cache block mapping, non-contiguous physical page allocation, zero-copy fragmentation tracking, radix-trie prefix caching, INT8 quantized compute, and speculative decoding verification. It also exposes prefill and decode latency telemetry so edge deployments can be benchmarked and tuned without external dependencies.
Setup details
This source describes a project but provides no normalized endpoint or package identifier. Follow its source listing for setup instructions.
Sources and provenance
- Glama source codeOfficial · Observed
Grouping basis: listing. Exact endpoints or package sets can be grouped automatically; other relationships require evidence review. This does not verify publisher affiliation, connection health, or equivalent capabilities.