]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
ggml : use WARP_SIZE/2 for argmax reduction offset (#18092)
authorAadeshveer Singh <redacted>
Wed, 17 Dec 2025 03:47:01 +0000 (09:17 +0530)
committerGitHub <redacted>
Wed, 17 Dec 2025 03:47:01 +0000 (11:47 +0800)
commit58062860afb88e555857c1266d3a17e1b65b5eb9
tree5512b2fb692f0ad4b4a23da9f758f22facea39f0
parent2973a65ecb6c884ca609de6eb5f1b6dc08631aaf
ggml : use WARP_SIZE/2 for argmax reduction offset (#18092)
ggml/src/ggml-cuda/argmax.cu