]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
CUDA: enable FA for FP32 KV cache (llama/16546)
authorJohannes Gäßler <redacted>
Tue, 14 Oct 2025 12:22:47 +0000 (14:22 +0200)
committerGeorgi Gerganov <redacted>
Wed, 15 Oct 2025 06:29:17 +0000 (09:29 +0300)
commit1bdd746bc8989733075c6e321e517b4ef0f6c203
treed299eb925f32c8e92061b0b877785064681cb946
parentf2075667fa872b95b8afa3517f938432ffb488ba
CUDA: enable FA for FP32 KV cache (llama/16546)
ggml/src/ggml-cuda/fattn-vec.cuh
ggml/src/ggml-cuda/fattn.cu