llama.cpp
68d0027f - ggml-cpu: faster AVX2 variant for IQ1_M (#12216)

Commit

96 days ago

ggml-cpu: faster AVX2 variant for IQ1_M (#12216)

References

#12216 - ggml-cpu: faster AVX2 variant for IQ1_M

Author

remyoudompheng

remyoudompheng

Parents

Files1

ggml/src/ggml-cpu
- ggml-cpu-quants.c