]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : remove KV cache defragmentation logic (#15473)
authorGeorgi Gerganov <redacted>
Fri, 22 Aug 2025 09:22:13 +0000 (12:22 +0300)
committerGitHub <redacted>
Fri, 22 Aug 2025 09:22:13 +0000 (12:22 +0300)
commit9ebebef62fd0adf8685874f154e227ea87b7c6f4
tree74a04bbb9f8cd24843210b44e088b60fb52c134e
parentad5c975c2d0297124fad210776ef8eed6b90d578
llama : remove KV cache defragmentation logic (#15473)

ggml-ci
16 files changed:
common/arg.cpp
common/common.cpp
common/common.h
examples/llama.vim
include/llama.h
scripts/compare-llama-bench.py
src/llama-context.cpp
src/llama-cparams.h
src/llama-kv-cache.cpp
src/llama-kv-cache.h
src/llama-kv-cells.h
src/llama-memory.h
tools/llama-bench/README.md
tools/llama-bench/llama-bench.cpp
tools/server/README.md
tools/server/bench/bench.py