Thireus ☠ 6d78a87c4c perplexity: signal-driven hot-swap mode for persistent per-tensor PPL/KLD benchmarking (extends #1989) (#2131) ... * perplexity: add signal-driven hot-swap mode for persistent KLD/PPL benchmarking llama-perplexity can now stay resident and be driven through control/status files (reload/compute/exit): it reloads only the tensors that changed on disk and recomputes PPL/KLD without ever reloading the full model. File-based signalling works on Windows, macOS and Linux. The reload returning-to-original path now refreshes tensor data from disk instead of reattaching stale weights. * Not Cygwin specific		2026-07-14 12:56:03 +03:00
..
llama-star	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
HOWTO-add-model.md	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
debugging-tests.md	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
on-demand-tensor-reload.md	perplexity: signal-driven hot-swap mode for persistent per-tensor PPL/KLD benchmarking (extends #1989) (#2131)	2026-07-14 12:56:03 +03:00
on-demand-tensor-reload.mmd	on-demand tensor reload (#1989)	2026-06-22 16:36:34 +02:00
parsing.md	Autoparser - complete refactoring of parser architecture (#1376)	2026-04-22 10:04:13 +02:00
token_generation_performance_tips.md	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00