vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : add phi3 128K model support (#7225)

Browse source 
* add phi3 128k support in convert-hf-to-gguf

* add phi3 128k support in cuda

* address build warnings on llama.cpp

* adjust index value in cuda long rope freq factors

* add long rope support in ggml cpu backend

* make freq factors only depend on ctx size

* remove unused rope scaling type 'su' frin gguf converter

* fix flint warnings on convert-hf-to-gguf.py

* set to the short freq factor when context size is small than trained context size

* add one line of comments

* metal : support rope freq_factors

* ggml : update ggml_rope_ext API to support freq. factors

* backends : add dev messages to support rope freq. factors

* minor : style

* tests : update to use new rope API

* backends : fix pragma semicolons

* minor : cleanup

* llama : move rope factors from KV header to tensors

* llama : remove tmp assert

* cuda : fix compile warning

* convert : read/write n_head_kv

* llama : fix uninitialized tensors

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
liuwei-git 2024-05-22 04:28:32 +08:00 • committed by GitHub
parent 6369bf0433
commit 201cc11afa
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 484 additions and 233 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ggml-metal.metal
View file

@ -1640,6 +1640,7 @@ static void rope_yarn_corr_dims(
typedef void (rope_t)(
device const void * src0,
device const int32_t * src1,
device const float * src2,
device float * dst,
constant int64_t & ne00,
constant int64_t & ne01,
@ -1675,6 +1676,7 @@ template<typename T>
kernel void kernel_rope(
device const void * src0,
device const int32_t * src1,
device const float * src2,
device float * dst,
constant int64_t & ne00,
constant int64_t & ne01,
@ -1744,8 +1746,10 @@ kernel void kernel_rope(
// simplified from `(ib * n_dims + ic) * inv_ndims`
const float cur_rot = inv_ndims*ic - ib;
const float freq_factor = src2 != src0 ? src2[ic/2] : 1.0f;
const float theta = theta_0 * pow(freq_base, cur_rot) / freq_factor;
const float theta = theta_0 * pow(freq_base, cur_rot);
float cos_theta, sin_theta;
rope_yarn(theta, freq_scale, corr_dims, cur_rot, ext_factor, attn_factor, &cos_theta, &sin_theta);