vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-11 04:51:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	common/CMakeLists.txt
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/scale.cl
#	ggml/src/ggml-sycl/backend.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2025-07-10 17:43:08 +08:00
commit c52cbdce52
22 changed files with 774 additions and 496 deletions
Download patch file Download diff file Expand all files Collapse all files

13
src/llama-memory-recurrent.cpp
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));
}