]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
cuda : fix defrag with quantized KV (llama/9319)
authorslaren <redacted>
Thu, 5 Sep 2024 09:13:11 +0000 (11:13 +0200)
committerGeorgi Gerganov <redacted>
Sun, 8 Sep 2024 11:43:07 +0000 (14:43 +0300)
commitaed99d2b5e6de20732eefc4ccb91a97633ab48f6
tree81bd4f6da9fd06c53da34ccf506f4c881f8168d4
parentb7b2f64afb66ea8e8858a93d1c4be511b86aba1f
cuda : fix defrag with quantized KV (llama/9319)
src/ggml-backend.c
src/ggml-cuda.cu
src/ggml-cuda/cpy.cu