llama : set n_outputs to 1 to avoid 0 outputs mean-pooling (#15791)

* llama : set n_outputs to 1 to avoid 0 outputs mean-pooling

This commit modifies the llama_context constructor to set n_outputs to
1.

The motivation for this is that when using pooling, and specifically
mean pooling, for embeddings having n_outputs set to 0 can lead to the
following error:
```console
$ build/bin/llama-embedding -m models/nomic-embed-text-1.5-Q4_K_M.gguf \
   --pooling mean -p "Hello, how are you?"
...
llama_context:        CPU  output buffer size =     0.12 MiB
/home/danbev/work/ai/llama.cpp/ggml/src/ggml.c:3023: GGML_ASSERT(ggml_can_mul_mat(a, b)) failed
0x0000743c96d107e3 in __GI___wait4 (pid=292978, stat_loc=0x0, options=0, usage=0x0) at ../sysdeps/unix/sysv/linux/wait4.c:30
warning: 30	../sysdeps/unix/sysv/linux/wait4.c: No such file or directory
30	in ../sysdeps/unix/sysv/linux/wait4.c
196	        waitpid(child_pid, NULL, 0);
230	        ggml_print_backtrace();
3023	    GGML_ASSERT(ggml_can_mul_mat(a, b));
1823	                cur = ggml_mul_mat(ctx0, ggml_cont(ctx0, ggml_transpose(ctx0, inp)), inp_mean);
18983	    llm->build_pooling(cls, cls_b, cls_out, cls_out_b);
1399	    auto * gf = model.build_graph(gparams);
292	            auto * gf = graph_reserve(1, n_seqs, n_outputs, mctx.get(), true);
2329	        auto * ctx = new llama_context(*model, params);
913	    llama_context * lctx = llama_init_from_model(model, cparams);
105	    common_init_result llama_init = common_init_from_params(params);
[Inferior 1 (process 292976) detached]
Aborted (core dumped)
```

Co-authored-by: Georgi Gerganov <redacted>
* add comment about not reserving graphs with zero outputs

* add assert in graph_reserve to ensure n_outputs >= 1

---------

Co-authored-by: Georgi Gerganov <redacted>

diff --git a/src/llama-context.cpp b/src/llama-context.cpp
index 2de6fcf0cb20909aa5b393a564a4d68c69e578b1..6b3188be4bc015dc11db3939388ae21ec33de8fe 100644 (file)
--- a/src/llama-context.cpp
+++ b/src/llama-context.cpp
@@ -285,6 +285,9 @@ llama_context::llama_context(
         const uint32_t n_seqs = cparams.kv_unified ? 1 : cparams.n_seq_max;
         const uint32_t n_tokens = std::min(cparams.n_ctx, cparams.n_ubatch);
 
+        // avoid reserving graphs with zero outputs
+        n_outputs = 1;
+
         LLAMA_LOG_DEBUG("%s: worst-case: n_tokens = %d, n_seqs = %d, n_outputs = %d\n", __func__, n_tokens, n_seqs, n_outputs);
 
         // resolve automatic Flash Attention use
@@ -1368,6 +1371,7 @@ llm_graph_result * llama_context::get_gf_res_reserve() const {
 
 ggml_cgraph * llama_context::graph_reserve(uint32_t n_tokens, uint32_t n_seqs, uint32_t n_outputs, const llama_memory_context_i * mctx, bool split_only) {
     LLAMA_LOG_DEBUG("%s: reserving a graph for ubatch with n_tokens = %4u, n_seqs = %2u, n_outputs = %4u\n", __func__, n_tokens, n_seqs, n_outputs);
+    GGML_ASSERT(n_outputs >= 1);
 
     if (n_tokens % n_seqs != 0) {
         n_tokens = ((n_tokens + (n_seqs - 1)) / n_seqs) * n_seqs; // round to next multiple of n_seqs