matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-12 00:37:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

llm: update llama.cpp commit to 8962422 (#6618)

Browse Source
This commit is contained in:
Jeffrey Morgan
2024-09-03 21:12:39 -04:00
committed by GitHub
parent f29b167e1a
commit 5e2653f9fe
7 changed files with 32 additions and 422 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
llm/patches/06-embeddings.diff
View File

@@ -1,37 +1,36 @@
diff --git a/src/llama.cpp b/src/llama.cpp
index 1fe2b9f7..a43312a7 100644
index 88355971..d7db689b 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -13689,7 +13689,7 @@ static size_t llama_output_reserve(llama_context & lctx, size_t n_outputs) {
@@ -15906,7 +15906,7 @@ static size_t llama_output_reserve(llama_context & lctx, size_t n_outputs) {
const auto n_embd = hparams.n_embd;
// TODO: use a per-batch flag for logits presence instead
- const bool has_logits = !cparams.embeddings;
+ const bool has_logits = cparams.causal_attn;
const bool has_embd = lctx.is_encoding || (cparams.embeddings && (cparams.pooling_type == LLAMA_POOLING_TYPE_NONE));
const bool has_embd = cparams.embeddings && (cparams.pooling_type == LLAMA_POOLING_TYPE_NONE);
const size_t logits_size = has_logits ? n_vocab*n_outputs_max : 0;
@@ -13959,17 +13959,25 @@ static int llama_decode_internal(
@@ -16175,20 +16175,23 @@ static int llama_decode_internal(
// no output
res = nullptr;
embd = nullptr;
- } else if (cparams.embeddings) {
- res = nullptr; // do not extract logits for embedding case
- embd = gf->nodes[gf->n_nodes - 1];
- if (strcmp(embd->name, "result_embd_pooled") != 0) {
- embd = gf->nodes[gf->n_nodes - 2];
- res = nullptr; // do not extract logits for embedding case
- embd = nullptr;
+ }
+
+ if (cparams.embeddings) {
+ for (int i = gf->n_nodes - 1; i >= 0; --i) {
for (int i = gf->n_nodes - 1; i >= 0; --i) {
- if (strcmp(gf->nodes[i]->name, "result_embd_pooled") == 0) {
- embd = gf->nodes[i];
+ embd = gf->nodes[i];
+ if (strcmp(embd->name, "result_embd_pooled") == 0) {
+ break;
+ }
break;
}
}
GGML_ASSERT(strcmp(embd->name, "result_embd_pooled") == 0 && "missing embeddings tensor");
- } else {
+ } else {
- GGML_ASSERT(embd != nullptr && "missing embeddings tensor");
} else {
embd = nullptr; // do not extract embeddings when not needed
GGML_ASSERT(strcmp(res->name, "result_output") == 0 && "missing result_output tensor");
}
@@ -39,7 +38,6 @@ index 1fe2b9f7..a43312a7 100644
+ if (!cparams.causal_attn) {
+ res = nullptr; // do not extract logits when not needed
+ }
+
// 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);
ggml_backend_sched_alloc_graph(lctx.sched, gf);