]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
CUDA: faster dequantize kernels for Q4_0 and Q4_1 (llama/4938)
authorKawrakow <redacted>
Mon, 15 Jan 2024 05:48:06 +0000 (07:48 +0200)
committerGeorgi Gerganov <redacted>
Wed, 17 Jan 2024 19:21:09 +0000 (21:21 +0200)
commit161b51d91a7ebab67f9e4649b0ecf220c1f0b3be
tree797aea6968cb505b37ccfd22356de1c68999727e
parentf904b31a7df503daef5678c051828e81ba99ddec
CUDA: faster dequantize kernels for Q4_0 and Q4_1 (llama/4938)

Co-authored-by: Iwan Kawrakow <redacted>
ggml-cuda.cu