llama : add phi-2 + fix NeoX rope + ggml_mul_mat_set_prec (#4490)

* phi2 implementation

* fix breaking change

* phi-2 : various fixes

* phi-2 : use layer norm eps

* py : whitespaces

* llama : fix meta KV override bug

* convert : phi don't add BOS token

* convert : revert "added_tokens_decoder" change

* phi-2 : scale Q instead of KQ for better precision

* ggml : fix NeoX rope to rotate just first n_dims

* cuda : less diff in the rope_neox kernel

* ggml : add ggml_mul_mat_set_prec

ggml-ci

* Update ggml-cuda.cu

Co-authored-by: slaren <slarengh@gmail.com>

* Update ggml-cuda.cu

Co-authored-by: slaren <slarengh@gmail.com>

* cuda : ggml_cuda_op_mul_mat_cublas support F32 precision

* cuda : remove oboslete comment

---------

Co-authored-by: Ebey Abraham <ebeyabraham@microsoft.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Ebey Abraham 2023-12-18 17:27:47 +00:00 committed by GitHub
parent 3c04bf6da8
commit b9e74f9bca
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 463 additions and 76 deletions

View file

@ -1702,8 +1702,9 @@ kernel void kernel_rope(
dst_data[1] = x0*sin_theta + x1*cos_theta;
}
} else {
for (int64_t ib = 0; ib < ne0/n_dims; ++ib) {
for (int64_t ic = 2*tiitg; ic < n_dims; ic += 2*tptg.x) {
for (int64_t ic = 2*tiitg; ic < ne0; ic += 2*tptg.x) {
if (ic < n_dims) {
const int64_t ib = 0;
// simplified from `(ib * n_dims + ic) * inv_ndims`
const float cur_rot = inv_ndims*ic - ib;
@ -1722,6 +1723,14 @@ kernel void kernel_rope(
dst_data[0] = x0*cos_theta - x1*sin_theta;
dst_data[n_dims/2] = x0*sin_theta + x1*cos_theta;
} else {
const int64_t i0 = ic;
device const T * const src = (device T *)((device char *) src0 + i3*nb03 + i2*nb02 + i1*nb01 + i0*nb00);
device T * dst_data = (device T *)((device char *) dst + i3*nb3 + i2*nb2 + i1*nb1 + i0*nb0);
dst_data[0] = src[0];
dst_data[1] = src[1];
}
}
}