Skip to content

Fix Metal backend broken from the allocator changes #2455

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jul 31, 2023
Merged

Fix Metal backend broken from the allocator changes #2455

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
485bbe1
fix Metal backend broken from the allocator changes
slaren Jul 30, 2023
74fb31b
move asserts
slaren Jul 30, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 10 additions & 7 deletions llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1812,6 +1812,12 @@ static bool llama_eval_internal(
// otherwise, the threads are spin-lock waiting for the BLAS calls and are degrading the performance
n_threads = N >= 32 && ggml_cpu_has_blas() && !ggml_cpu_has_gpublas() ? 1 : n_threads;

struct ggml_tensor * res = gf->nodes[gf->n_nodes - 1];
struct ggml_tensor * embeddings = gf->nodes[gf->n_nodes - 2];

LLAMA_ASSERT(strcmp(res->name, "result_output") == 0);
LLAMA_ASSERT(strcmp(embeddings->name, "result_norm") == 0);

#if GGML_USE_MPI
const int64_t n_layer = hparams.n_layer;
ggml_mpi_graph_compute_pre(lctx.ctx_mpi, gf, n_layer);
Expand All @@ -1825,7 +1831,10 @@ static bool llama_eval_internal(
//}
ggml_metal_set_n_cb (lctx.ctx_metal, n_threads);
ggml_metal_graph_compute(lctx.ctx_metal, gf);
ggml_metal_get_tensor (lctx.ctx_metal, cur);
ggml_metal_get_tensor (lctx.ctx_metal, res);
if (!lctx.embedding.empty()) {
ggml_metal_get_tensor(lctx.ctx_metal, embeddings);
}
} else {
// IMPORTANT:
// Since we don't have efficient Matrix x Matrix Metal multiplication yet, we fallback to vanilla
Expand Down Expand Up @@ -1856,12 +1865,6 @@ static bool llama_eval_internal(
// update kv token count
lctx.kv_self.n = n_past + N;

struct ggml_tensor * res = gf->nodes[gf->n_nodes - 1];
struct ggml_tensor * embeddings = gf->nodes[gf->n_nodes - 2];

LLAMA_ASSERT(strcmp(res->name, "result_output") == 0);
LLAMA_ASSERT(strcmp(embeddings->name, "result_norm") == 0);

if (cgraph_fname) {
ggml_graph_export(gf, cgraph_fname);
}
Expand Down