From 16bc66d9479edd5ee12ec734973554d4493c5dfa Mon Sep 17 00:00:00 2001 From: slaren Date: Thu, 28 Sep 2023 21:42:38 +0200 Subject: llama.cpp : split llama_context_params into model and context params (#3301) * llama.cpp : split llama_context_params into model and context params ggml-ci * fix metal build * fix freq_base/scale default to model value * llama-bench : keep the same model between tests when possible * move n_threads to llama_context_params, add n_threads_batch * fix mpi build * remove kv_size(), cuda scratch fixes * remove low-vram option * add n_threads_batch to system info, refactor to get_system_info() * add documentation about --threads-batch to the READMEs * llama-bench fix * main : fix rope freq/scale warning * llama.cpp : add llama_get_model common : add llama_tokenize from model * remove duplicated ctx/model functions ggml-ci * cuda : print total VRAM used --- examples/parallel/parallel.cpp | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'examples/parallel/parallel.cpp') diff --git a/examples/parallel/parallel.cpp b/examples/parallel/parallel.cpp index 790189af..0434ded2 100644 --- a/examples/parallel/parallel.cpp +++ b/examples/parallel/parallel.cpp @@ -108,7 +108,7 @@ int main(int argc, char ** argv) { fflush(stderr); const int n_ctx = llama_n_ctx(ctx); - const int n_vocab = llama_n_vocab(ctx); + const int n_vocab = llama_n_vocab(model); std::vector clients(n_clients); for (size_t i = 0; i < clients.size(); ++i) { @@ -153,7 +153,7 @@ int main(int argc, char ** argv) { batch.logits[i] = false; } - if (llama_decode(ctx, batch, params.n_threads) != 0) { + if (llama_decode(ctx, batch) != 0) { LOG_TEE("%s: llama_decode() failed\n", __func__); return 1; } @@ -272,7 +272,7 @@ int main(int argc, char ** argv) { 0, 0, 0, // unused }; - const int ret = llama_decode(ctx, batch_view, params.n_threads); + const int ret = llama_decode(ctx, batch_view); if (ret != 0) { if (n_batch == 1 || ret < 0) { // if you get here, it means the KV cache is full - try increasing it via the context size -- cgit v1.2.3