ik_llama.cpp

mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-07-20 09:45:35 +00:00

Files

T

History

Thireus ☠andGitHub 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

backend

Merge mainline - Aug 12 2024 (#17 )

2024-08-12 15:14:32 +02:00

development

perplexity: signal-driven hot-swap mode for persistent per-tensor PPL/KLD benchmarking (extends #1989 ) (#2131 )

2026-07-14 12:56:03 +03:00

android.md

Merge mainline llama.cpp (#3 )

2024-07-27 07:55:01 +02:00

autoparser.md

common: handle Laguna chat delimiters (#1943 )