]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : disable graph reuse with pipeline parallelism (#20463)
authorGeorgi Gerganov <redacted>
Thu, 12 Mar 2026 19:04:13 +0000 (21:04 +0200)
committerGitHub <redacted>
Thu, 12 Mar 2026 19:04:13 +0000 (21:04 +0200)
commit57819b8d4b39d893408e51520dff3d47d1ebb757
tree76636870d15a035e9ff10836ea12fa57796b45bd
parent557fe2d9132913eaf08c8abf21b0cff61addb9ac
llama : disable graph reuse with pipeline parallelism (#20463)
ggml/src/ggml-backend.cpp
ggml/src/ggml-cuda/ggml-cuda.cu
src/llama-context.cpp