llama.cpp
58137f0f - quant : allow quantization of ffn_gate_inp tensors

Commit

103 days ago

quant : allow quantization of ffn_gate_inp tensors

References

gg/quant-allow-ffn-gate-inp

#26584 - quant : allow quantization of ffn_gate_inp tensors

Author

ggerganov

ggerganov

Parents

Loading