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

llm : support Adept Persimmon 8B (#3410)

Browse source 
* Produces garbage output

* wip: correct tensors up to RoPE

* correct tensors thru RoPE

* Correct outputs through masked & softmax'd KQ

* fp32 works

* Rename adept->persimmon

* Produces correct outputs

* clean up convert scripts

* remove printing logic from ggml.c

* remove prints from llama.cpp & fix merge

* trivial cleanups

* Add offload funcs

* update conversion script to directly take adept artifacts rather than .saftensors file

* Fix norm eps bug

* Support sqr and concat on metal, persimmon-8b-q4 runs correctly

* Small changes from review

* Formatting changes

* Minor changes to conversion script

* Remove old script

* Fix editorconfig formatting

* Fix build

* add overlooked offload code ggml-ci
This commit is contained in:
Phillip Kravtsov 2023-10-07 00:12:43 -07:00 • committed by GitHub
parent 3a716b4dae
commit 0e797c2fc5
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 854 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

54
ggml-metal.m
View file

@ -109,6 +109,8 @@ struct ggml_metal_context {
GGML_METAL_DECL_KERNEL(cpy_f32_f16);
GGML_METAL_DECL_KERNEL(cpy_f32_f32);
GGML_METAL_DECL_KERNEL(cpy_f16_f16);
GGML_METAL_DECL_KERNEL(concat);
GGML_METAL_DECL_KERNEL(sqr);
#undef GGML_METAL_DECL_KERNEL
};
@ -300,6 +302,8 @@ struct ggml_metal_context * ggml_metal_init(int n_cb) {
GGML_METAL_ADD_KERNEL(cpy_f32_f16);
GGML_METAL_ADD_KERNEL(cpy_f32_f32);
GGML_METAL_ADD_KERNEL(cpy_f16_f16);
GGML_METAL_ADD_KERNEL(concat);
GGML_METAL_ADD_KERNEL(sqr);
#undef GGML_METAL_ADD_KERNEL
}
@ -375,6 +379,8 @@ void ggml_metal_free(struct ggml_metal_context * ctx) {
GGML_METAL_DEL_KERNEL(cpy_f32_f16);
GGML_METAL_DEL_KERNEL(cpy_f32_f32);
GGML_METAL_DEL_KERNEL(cpy_f16_f16);
GGML_METAL_DEL_KERNEL(concat);
GGML_METAL_DEL_KERNEL(sqr);
#undef GGML_METAL_DEL_KERNEL
@ -766,6 +772,43 @@ void ggml_metal_graph_compute(
{
// noop
} break;
case GGML_OP_CONCAT:
{
int64_t nb = ne00;
[encoder setComputePipelineState:ctx->pipeline_concat];
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
[encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
[encoder setBuffer:id_dst offset:offs_dst atIndex:2];
[encoder setBytes:&ne00 length:sizeof(ne00) atIndex:3];
[encoder setBytes:&ne01 length:sizeof(ne01) atIndex:4];
[encoder setBytes:&ne02 length:sizeof(ne02) atIndex:5];
[encoder setBytes:&ne03 length:sizeof(ne03) atIndex:6];
[encoder setBytes:&nb00 length:sizeof(nb00) atIndex:7];
[encoder setBytes:&nb01 length:sizeof(nb01) atIndex:8];
[encoder setBytes:&nb02 length:sizeof(nb02) atIndex:9];
[encoder setBytes:&nb03 length:sizeof(nb03) atIndex:10];
[encoder setBytes:&ne10 length:sizeof(ne10) atIndex:11];
[encoder setBytes:&ne11 length:sizeof(ne11) atIndex:12];
[encoder setBytes:&ne12 length:sizeof(ne12) atIndex:13];
[encoder setBytes:&ne13 length:sizeof(ne13) atIndex:14];
[encoder setBytes:&nb10 length:sizeof(nb10) atIndex:15];
[encoder setBytes:&nb11 length:sizeof(nb11) atIndex:16];
[encoder setBytes:&nb12 length:sizeof(nb12) atIndex:17];
[encoder setBytes:&nb13 length:sizeof(nb13) atIndex:18];
[encoder setBytes:&ne0 length:sizeof(ne0) atIndex:19];
[encoder setBytes:&ne1 length:sizeof(ne1) atIndex:20];
[encoder setBytes:&ne2 length:sizeof(ne2) atIndex:21];
[encoder setBytes:&ne3 length:sizeof(ne3) atIndex:22];
[encoder setBytes:&nb0 length:sizeof(nb0) atIndex:23];
[encoder setBytes:&nb1 length:sizeof(nb1) atIndex:24];
[encoder setBytes:&nb2 length:sizeof(nb2) atIndex:25];
[encoder setBytes:&nb3 length:sizeof(nb3) atIndex:26];
[encoder setBytes:&nb length:sizeof(nb) atIndex:27];
const int nth = MIN(1024, ne0);
[encoder dispatchThreadgroups:MTLSizeMake(ne1, ne2, ne3) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
} break;
case GGML_OP_ADD:
{
GGML_ASSERT(ggml_is_contiguous(src0));
@ -903,6 +946,17 @@ void ggml_metal_graph_compute(
GGML_ASSERT(false);
}
} break;
case GGML_OP_SQR:
{
GGML_ASSERT(ggml_is_contiguous(src0));
[encoder setComputePipelineState:ctx->pipeline_sqr];
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
[encoder setBuffer:id_dst offset:offs_dst atIndex:1];
const int64_t n = ggml_nelements(dst);
[encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
} break;
case GGML_OP_SOFT_MAX:
{
const int nth = MIN(32, ne00);