12017)

Commit

337 days ago

metal : copy kernels for quant to F32/F16 conversions (llama/12017) metal: use dequantize_q templates --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

References

#2844 - sync : ggml

Author

gcp

Committer

ggerganov

Parents

b43b9d92

whisper.cpp 4b60ff4f - metal : copy kernels for quant to F32/F16 conversions (llama/12017)

whisper.cpp
4b60ff4f - metal : copy kernels for quant to F32/F16 conversions (llama/12017)