Skip to content
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

fix embeddings when using CUDA #3657

Merged
merged 1 commit into from
Oct 17, 2023
Merged

fix embeddings when using CUDA #3657

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
19 changes: 13 additions & 6 deletions llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5903,6 +5903,13 @@ static int llama_decode_internal(

ggml_allocr_alloc_graph(lctx.alloc, gf);

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

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


#ifdef GGML_USE_CUBLAS
for (int i = 0; i < gf->n_leafs; i++) {
ggml_tensor * node = gf->leafs[i];
Expand All @@ -5920,6 +5927,12 @@ static int llama_decode_internal(
}

ggml_cuda_set_mul_mat_q(cparams.mul_mat_q);

// HACK: ggml-alloc may change the tensor backend when reusing a parent, so force output to be on the CPU here if needed
if (!lctx.embedding.empty()) {
embeddings->backend = GGML_BACKEND_CPU;
}
res->backend = GGML_BACKEND_CPU;
#endif

// LLAMA_LOG_INFO("graph build time: %.3f ms (%d nodes, %d leafs)\n", (ggml_time_us() - t_start_us)/1000.0, gf->n_nodes, gf->n_leafs);
Expand All @@ -5944,12 +5957,6 @@ static int llama_decode_internal(
n_threads = 1;
}

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

GGML_ASSERT(strcmp(res->name, "result_output") == 0);
GGML_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 Down
Loading