]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
CUDA: fastdiv, launch bounds for mmvq + q8_1 quant (llama/15802)
authorJohannes Gäßler <redacted>
Fri, 5 Sep 2025 14:07:02 +0000 (16:07 +0200)
committerGeorgi Gerganov <redacted>
Sat, 20 Sep 2025 10:42:50 +0000 (13:42 +0300)
commit6ff468cfaa14fb39cabcd1b7fc8d701419093c72
tree4e1a681bf37493d42071d65e7a46c307eac11f6f
parent4d6e1144b156c590882b8ebc50ab16afb2c4b5c1
CUDA: fastdiv, launch bounds for mmvq + q8_1 quant (llama/15802)

* CUDA: fastdiv, launch bounds for mmvq + q8_1 quant
ggml/src/ggml-cuda/common.cuh
ggml/src/ggml-cuda/mmvq.cu
ggml/src/ggml-cuda/quantize.cu