public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-08 23:41:15 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2026-05-02 15:02:42 +03:00
parent 18162bcf61
commit 4bf733672b
144 changed files with 3675 additions and 5535 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/llama-memory-recurrent.cpp
+5 -7
View File
@@ -1,5 +1,6 @@
#include "llama-memory-recurrent.h"
#include "ggml-backend.h"
#include "llama-impl.h"
#include "llama-io.h"
#include "llama-batch.h"
@@ -91,8 +92,8 @@ llama_memory_recurrent::llama_memory_recurrent(
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);
ggml_tensor * s = ggml_new_tensor_1d(ctx, type_s, hparams.n_embd_s()*mem_size);
ggml_tensor * r = ggml_new_tensor_2d(ctx, type_r, hparams.n_embd_r(), mem_size);
ggml_tensor * s = ggml_new_tensor_2d(ctx, type_s, hparams.n_embd_s(), mem_size);
ggml_format_name(r, "cache_r_l%d", i);
ggml_format_name(s, "cache_s_l%d", i);
r_l[i] = r;
@@ -928,11 +929,8 @@ bool llama_memory_recurrent::state_read_meta(llama_io_read_i & io, uint32_t cell
llama_seq_id seq_id;
io.read_to(&seq_id, sizeof(seq_id));
// TODO: llama_memory_recurrent should have a notion of max sequences
//if (seq_id < 0 || (uint32_t) seq_id >= llama_n_seq_max(ctx)) {
if (seq_id < 0) {
//LLAMA_LOG_ERROR("%s: invalid seq_id, %d is out of range [0, %u)\n", __func__, seq_id, llama_n_seq_max(ctx));
LLAMA_LOG_ERROR("%s: invalid seq_id, %d is out of range [0, inf)\n", __func__, seq_id);
if (seq_id < 0 || (uint32_t) seq_id >= this->n_seq_max) {
LLAMA_LOG_ERROR("%s: invalid seq_id, %d is out of range [0, %u)\n", __func__, seq_id, this->n_seq_max);
return false;
}