Indras-Mirror/llama.cpp-turboq-mtp
Fused TBQ4 Flash Attention + MTP + Shared Tensors + Qwen35 SWA Hybrid for llama.cpp — 82+ tok/s, lossless 4.25 bpv KV cache, SWA-bounded deep-context decode (w/ long-range recall) on RTX 4090
Health Breakdown
Should you contribute to Indras-Mirror/llama.cpp-turboq-mtp?
Indras-Mirror/llama.cpp-turboq-mtp has a FoundDev health score of 87/100, which puts it in the active-and-maintained tier. The maintainer team is shipping recently, issues are being closed, and a PR you open this week has a realistic chance of being reviewed.
Last push was 0 days ago — that signals an actively maintained project. New issues are likely to get a maintainer response within days. The project is written primarily in C++, so prior C++ experience will shorten ramp-up.
Licensed under MIT, a standard OSI-approved license — safe to contribute to under normal employer IP policies.
Community
