llama.cpp
c9c64dee - Set GLM4 blk..attn_output.weight, kqv_out- matmul to GGML_PREC_F32 to fix infinity values in output (#13639)

Commit

212 days ago

Set GLM4 blk.*.attn_output.weight, kqv_out-* matmul to GGML_PREC_F32 to fix infinity values in output (#13639)

References

Author

0cc4m

Parents

llama.cpp c9c64dee - Set GLM4 blk.*.attn_output.weight, kqv_out-* matmul to GGML_PREC_F32 to fix infinity values in output (#13639)