llama.cpp CUDA on RTX 5080: Llama-2-7B Q4_0 FA-off pp512 prefill tok/s (scoreboard #15013)

COMMUNITY-SCOREBOARD (llama.cpp discussion #15013, maintainer-curated). llama-bench -m llama-2-7b.Q4_0.gguf -ngl 99 -fa 0. RTX 5080 (16 GB GDDR7 256-bit). Build commit 8a4280c, reporter @Hedede. llama-bench default -r 5 repeats, mean +/- std (±9.5). Single-GPU run per thread rules. Per-request batch-1, NOT aggregate.

Maintainer-verified scoreboard row from ggml-org/llama.cpp#15013. Identical model/test/flags across every GPU, making this the cleanest cross-GPU llama.cpp comparison in the repo. tg128 is bandwidth-bound and tracks memory bandwidth; pp512 tracks compute. Non-FA baseline.