]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
kv-cache : use ggml_set_rows (#14285)
authorGeorgi Gerganov <redacted>
Thu, 3 Jul 2025 07:53:35 +0000 (10:53 +0300)
committerGitHub <redacted>
Thu, 3 Jul 2025 07:53:35 +0000 (10:53 +0300)
commita70c8a0c4b4c1606cd9a0ba889ce61aa88610095
tree6069e4e9eddd54c45a09491ae2c03d438f17dae6
parent9067487c4411efb20400103fcccfdd389c80d428
kv-cache : use ggml_set_rows (#14285)

* kv-cache : use ggml_set_rows

ggml-ci

* graph : separate k and v indices

ggml-ci

* cont : remove redundant ifs

ggml-ci

* kv-cache : improve find_slot impl

* kv-cache : bounds-check when accessing slot_info indices

* kv-cache : add comments

ggml-ci

* ggml : add TODOs for adding GGML_OP_SET_ROWS support in the backends

ggml-ci
13 files changed:
ggml/src/ggml-cann/ggml-cann.cpp
ggml/src/ggml-opencl/ggml-opencl.cpp
ggml/src/ggml-sycl/ggml-sycl.cpp
ggml/src/ggml-vulkan/ggml-vulkan.cpp
src/llama-graph.cpp
src/llama-graph.h
src/llama-kv-cache-unified-iswa.cpp
src/llama-kv-cache-unified-iswa.h
src/llama-kv-cache-unified.cpp
src/llama-kv-cache-unified.h
src/llama-kv-cells.h
src/llama-memory-hybrid.cpp
src/llama-memory-hybrid.h