]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
batched-bench : fix llama_synchronize usage during prompt processing (#15835)
authorGeorgi Gerganov <redacted>
Mon, 8 Sep 2025 07:27:07 +0000 (10:27 +0300)
committerGitHub <redacted>
Mon, 8 Sep 2025 07:27:07 +0000 (10:27 +0300)
commita885dcff11a7b73f9377812d6151f6b15d307de0
tree3a818d9175384d7a0b6789de97a17a44704b162e
parent663027fd5490438ce9c27ea866a560e1e268d11f
batched-bench : fix llama_synchronize usage during prompt processing (#15835)

ggml-ci
tools/batched-bench/batched-bench.cpp