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

llama : ggml-backend integration (#4766)

Browse source 
* llama : ggml-backend integration

* ggml-backend : add names to buffers

* fix unmap after loading

* batched-bench : add tensor_split param

* llama : check for null tensor_split

* ggml-backend : increase GGML_MAX_BACKENDS

* improve graph splitting, partial fix for --no-kv-offload

* cuda : add ggml-backend split buffer support

* cuda : do not create buffer types for devices that don't exist (fixes usage without CUDA devices available)

* ggml : fix null backend dereference (#4807)

* ggml : fix null backend dereference

* ggml : also check ggml_backend_is_cpu

* test-backend-ops : check buffer allocation failures

* llama : add cparam (split_mode) and command line argument (--split-mode, -sm) to configure the split mode (none, layer or row)

* ggml : fix mul_mat_id work size

* llama : rewrite session kv load/set without graphs

* minor

* llama : only initialize used backends, free backends on context free

* llama : abort ctx if cuda backend init fails

* llama : rewrite lora with ggml-backend and compute on CPU

ggml-ci

* llama : only map to a backend buffer the region of the file mapping containing the tensors used in the buffer

* opencl : add ggml-backend buffer type

* cuda : only use batched_cublas with batched mat muls (fixes fp16 tg perf)

* llama : on Metal, by default offload the full model

ggml-ci

* metal : page align the data ptr (#4854)

* Apply suggestions from code review

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* cuda : fix split buffer free

* address review comments

* llama-bench : add split-mode parameter

* fix whitespace

* opencl : fix double initialization

* server : add --split-mode parameter

* use async copy and compute to improve multi-gpu performance

ggml-ci

* use async memcpys to copy the graph outputs to the CPU

* fix opencl

* use a host buffer for the cpu compute buffer for faster copies to the gpu

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
slaren 2024-01-12 20:07:38 +01:00 • committed by GitHub
parent 584d674be6
commit e7e4df031b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
21 changed files with 2533 additions and 2295 deletions
Download patch file Download diff file Expand all files Collapse all files

30
ggml.c
View file

@ -2354,6 +2354,10 @@ struct ggml_context * ggml_init(struct ggml_init_params params) {
}
void ggml_free(struct ggml_context * ctx) {
if (ctx == NULL) {
return;
}
// make this function thread safe
ggml_critical_section_start();
@ -4362,6 +4366,23 @@ struct ggml_tensor * ggml_cpy(
return ggml_cpy_impl(ctx, a, b);
}
struct ggml_tensor * ggml_cast(
struct ggml_context * ctx,
struct ggml_tensor * a,
enum ggml_type type) {
bool is_node = false;
struct ggml_tensor * result = ggml_new_tensor(ctx, type, GGML_MAX_DIMS, a->ne);
ggml_format_name(result, "%s (copy)", a->name);
result->op = GGML_OP_CPY;
result->grad = is_node ? ggml_dup_tensor(ctx, result) : NULL;
result->src[0] = a;
result->src[1] = result;
return result;
}
// ggml_cont
static struct ggml_tensor * ggml_cont_impl(
@ -14871,7 +14892,7 @@ size_t ggml_hash_find_or_insert(struct ggml_hash_set hash_set, struct ggml_tenso
return i;
}
static struct ggml_hash_set ggml_hash_set_new(size_t size) {
struct ggml_hash_set ggml_hash_set_new(size_t size) {
size = ggml_hash_size(size);
struct ggml_hash_set result;
result.size = size;
@ -16620,7 +16641,7 @@ static thread_ret_t ggml_graph_compute_thread(void * data) {
return GGML_EXIT_SUCCESS;
}
struct ggml_cplan ggml_graph_plan(struct ggml_cgraph * cgraph, int n_threads) {
struct ggml_cplan ggml_graph_plan(const struct ggml_cgraph * cgraph, int n_threads) {
if (n_threads <= 0) {
n_threads = GGML_DEFAULT_N_THREADS;
}
@ -16682,14 +16703,15 @@ struct ggml_cplan ggml_graph_plan(struct ggml_cgraph * cgraph, int n_threads) {
} break;
case GGML_OP_MUL_MAT_ID:
{
cur = 0;
const struct ggml_tensor * src0 = node->src[2];
const struct ggml_tensor * src1 = node->src[1];
const enum ggml_type vec_dot_type = type_traits[src0->type].vec_dot_type;
if (src1->type != vec_dot_type) {
cur = ggml_row_size(vec_dot_type, ggml_nelements(src1));
cur += ggml_row_size(vec_dot_type, ggml_nelements(src1));
}
const int n_as = ggml_get_op_params_i32(node, 1);
cur = GGML_PAD(cur, sizeof(int64_t)); // align
cur += GGML_PAD(cur, sizeof(int64_t)); // align
cur += n_as * sizeof(int64_t); // matrix_row_counts
cur += n_as * src1->ne[1] * sizeof(int64_t); // matrix_rows
} break;