From 0e89203b517c95ec6675eda75d200a60d1e8921d Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Wed, 18 Oct 2023 16:21:57 +0300 Subject: speculative : add tree-based sampling example (#3624) * sampling : one sequence per sampling context ggml-ci * speculative : add tree-based sampling support ggml-ci * speculative : reuse the n_parallel CLI param * speculative : refactor sampling * examples : fix build after sampling refactoring ggml-ci * batched : fix n_seq_id * sampling : fix malloc ggml-ci * swift : fix build ggml-ci * swift : try to fix build ggml-ci * prompts : add assistant.txt * common : add llama_batch_add() and llama_batch_clear() helpers * speculative : minor refactor ggml-ci * minor : comments + rename ggml-ci * speculative : fix off-by-one for n_drafted * speculative : fix the n_drafted fix + p constants --- examples/embd-input/embd-input-lib.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'examples/embd-input/embd-input-lib.cpp') diff --git a/examples/embd-input/embd-input-lib.cpp b/examples/embd-input/embd-input-lib.cpp index 87a5a1c2..3ce33842 100644 --- a/examples/embd-input/embd-input-lib.cpp +++ b/examples/embd-input/embd-input-lib.cpp @@ -79,7 +79,7 @@ bool eval_float(void * model, float * input, int N){ if (n_eval > n_batch) { n_eval = n_batch; } - llama_batch batch = { int32_t(n_eval), nullptr, (input+i*n_emb), nullptr, nullptr, nullptr, n_past, 1, 0, }; + llama_batch batch = { int32_t(n_eval), nullptr, (input+i*n_emb), nullptr, nullptr, nullptr, nullptr, n_past, 1, 0, }; if (llama_decode(ctx, batch)) { fprintf(stderr, "%s : failed to eval\n", __func__); return false; -- cgit v1.2.3