public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-05 22:11:21 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-12 19:23:56 +03:00
parent 6d64e4abf3
commit 6ddff4d96a
24 changed files with 2831 additions and 690 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/llama-memory-recurrent.cpp
+11 -9
View File
@@ -25,9 +25,6 @@ llama_memory_recurrent::llama_memory_recurrent(
uint32_t n_seq_max) : hparams(model.hparams), n_seq_max(n_seq_max) {
const int32_t n_layer = hparams.n_layer;
LLAMA_LOG_INFO("%s: mem_size = %u, n_seq_max = %u, type_r = '%s', type_s = '%s', n_layer = %d\n",
__func__, mem_size, n_seq_max, ggml_type_name(type_r), ggml_type_name(type_s), n_layer);
head = 0;
size = mem_size;
used = 0;
@@ -84,7 +81,7 @@ llama_memory_recurrent::llama_memory_recurrent(
ggml_context * ctx = ctx_for_buft(buft);
if (!ctx) {
throw std::runtime_error("failed to create ggml context for kv cache");
throw std::runtime_error("failed to create ggml context for rs cache");
}
ggml_tensor * r = ggml_new_tensor_1d(ctx, type_r, hparams.n_embd_r()*mem_size);
@@ -102,10 +99,10 @@ llama_memory_recurrent::llama_memory_recurrent(
ggml_backend_buffer_t buf = ggml_backend_alloc_ctx_tensors_from_buft(ctx, buft);
if (!buf) {
throw std::runtime_error("failed to allocate buffer for kv cache");
throw std::runtime_error("failed to allocate buffer for rs cache");
}
ggml_backend_buffer_clear(buf, 0);
LLAMA_LOG_INFO("%s: %10s KV buffer size = %8.2f MiB\n", __func__, ggml_backend_buffer_name(buf), ggml_backend_buffer_get_size(buf)/1024.0/1024.0);
LLAMA_LOG_INFO("%s: %10s RS buffer size = %8.2f MiB\n", __func__, ggml_backend_buffer_name(buf), ggml_backend_buffer_get_size(buf)/1024.0/1024.0);
bufs.emplace_back(buf);
}
@@ -113,8 +110,8 @@ llama_memory_recurrent::llama_memory_recurrent(
const size_t memory_size_r = size_r_bytes();
const size_t memory_size_s = size_s_bytes();
LLAMA_LOG_INFO("%s: KV self size = %7.2f MiB, R (%s): %7.2f MiB, S (%s): %7.2f MiB\n", __func__,
(float)(memory_size_r + memory_size_s) / (1024.0f * 1024.0f),
LLAMA_LOG_INFO("%s: size = %7.2f MiB (%6u cells, %3d layers, %2u seqs), R (%s): %7.2f MiB, S (%s): %7.2f MiB\n", __func__,
(float)(memory_size_r + memory_size_s) / (1024.0f * 1024.0f), mem_size, n_layer, n_seq_max,
ggml_type_name(type_r), (float)memory_size_r / (1024.0f * 1024.0f),
ggml_type_name(type_s), (float)memory_size_s / (1024.0f * 1024.0f));
}
@@ -374,7 +371,7 @@ llama_memory_context_ptr llama_memory_recurrent::init_batch(llama_batch_allocr &
// if all tokens are output, split by sequence
ubatch = balloc.split_seq(n_ubatch);
} else {
ubatch = balloc.split_equal(n_ubatch);
ubatch = balloc.split_equal(n_ubatch, false);
}
if (ubatch.n_tokens == 0) {
@@ -384,6 +381,11 @@ llama_memory_context_ptr llama_memory_recurrent::init_batch(llama_batch_allocr &
ubatches.push_back(std::move(ubatch)); // NOLINT
}
if (balloc.get_n_used() < balloc.get_n_tokens()) {
// failed to find a suitable split
break;
}
if (!prepare(ubatches)) {
break;
}