git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

overview / pkg / ggml / sources / llama.cpp / commit

summary | shortlog | log | commit | commitdiff | tree
(parent: 38ad381)

author	Johannes Gäßler <redacted>
	Sat, 30 Aug 2025 14:32:10 +0000 (16:32 +0200)
committer	GitHub <redacted>
	Sat, 30 Aug 2025 14:32:10 +0000 (16:32 +0200)
commit	e81b8e4b7f5ab870836fad26d154a7507b341b36
tree	4280194dd8e5532a99ffe382a732173ca19d7f37	tree
parent	38ad381f9f5d4dd368a96d844fb19cf501ed9d22	commit \| diff

llama: use FA + max. GPU layers by default (#15434)

* llama: use max. GPU layers by default, auto -fa

* ggml-backend: abort instead of segfault

19 files changed:

common/arg.cpp		diff \| blob \| history
common/common.cpp		diff \| blob \| history
common/common.h		diff \| blob \| history
examples/diffusion/diffusion-cli.cpp		diff \| blob \| history
ggml/src/ggml-backend.cpp		diff \| blob \| history
include/llama.h		diff \| blob \| history
scripts/server-bench.py		diff \| blob \| history
scripts/tool_bench.py		diff \| blob \| history
src/llama-context.cpp		diff \| blob \| history
src/llama-graph.cpp		diff \| blob \| history
src/llama-graph.h		diff \| blob \| history
src/llama-impl.h		diff \| blob \| history
src/llama-model.cpp		diff \| blob \| history
src/llama.cpp		diff \| blob \| history
tools/batched-bench/batched-bench.cpp		diff \| blob \| history
tools/llama-bench/llama-bench.cpp		diff \| blob \| history
tools/server/tests/unit/test_ctx_shift.py		diff \| blob \| history
tools/server/tests/unit/test_speculative.py		diff \| blob \| history
tools/server/tests/utils.py		diff \| blob \| history

Packaging of ggml-org/llama.cpp