vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 17:44:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge commit '72b090da2c' into concedo_experimental

Browse source 
# Conflicts:
#	docs/backend/CANN.md
#	docs/function-calling.md
#	examples/embedding/embedding.cpp
#	examples/retrieval/retrieval.cpp
#	ggml/src/ggml-cann/CMakeLists.txt
#	ggml/src/ggml-cann/Doxyfile
#	ggml/src/ggml-cann/acl_tensor.cpp
#	ggml/src/ggml-cann/acl_tensor.h
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-sycl/binbcast.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/concat.cpp
#	ggml/src/ggml-sycl/conv.cpp
#	ggml/src/ggml-sycl/cpy.cpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/getrows.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/gla.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/norm.cpp
#	ggml/src/ggml-sycl/outprod.cpp
#	ggml/src/ggml-sycl/rope.cpp
#	ggml/src/ggml-sycl/softmax.cpp
#	ggml/src/ggml-sycl/tsembd.cpp
#	ggml/src/ggml-sycl/wkv.cpp
#	scripts/compare-commits.sh
#	tests/test-chat.cpp
#	tests/test-sampling.cpp
This commit is contained in:
Concedo 2025-05-28 00:28:41 +08:00
commit 8c701d7ded
20 changed files with 380 additions and 221 deletions
Download patch file Download diff file Expand all files Collapse all files

16
src/llama-context.cpp
View file

@ -693,12 +693,18 @@ int llama_context::encode(llama_batch & inp_batch) {
GGML_ASSERT((!batch.token && batch.embd) || (batch.token && !batch.embd)); // NOLINT
// TODO: move the validation to the llama_batch_allocr
if (batch.token) {
for (int32_t i = 0; i < n_tokens; ++i) {
if (batch.token[i] < 0 || (uint32_t) batch.token[i] >= model.vocab.n_tokens()) {
LLAMA_LOG_ERROR("%s: invalid token[%d] = %d\n", __func__, i, batch.token[i]);
return -1;
}
if (batch.seq_id && (batch.seq_id[i][0] < 0 || batch.seq_id[i][0] >= LLAMA_MAX_PARALLEL_SEQUENCES)) {
LLAMA_LOG_ERROR("%s: invalid seq_id[%d] = %d > %d\n", __func__, i, batch.seq_id[i][0], LLAMA_MAX_PARALLEL_SEQUENCES);
throw -1;
}
}
}
@ -852,7 +858,7 @@ int llama_context::encode(llama_batch & inp_batch) {
int llama_context::decode(llama_batch & inp_batch) {
if (!memory) {
LLAMA_LOG_WARN("%s: cannot decode batches with this context (use llama_encode() instead)\n", __func__);
LLAMA_LOG_DEBUG("%s: cannot decode batches with this context (calling encode() instead)\n", __func__);
return encode(inp_batch);
}
@ -887,11 +893,17 @@ int llama_context::decode(llama_batch & inp_batch) {
GGML_ASSERT((!batch.token && batch.embd) || (batch.token && !batch.embd)); // NOLINT
// TODO: move the validation to the llama_batch_allocr
if (batch.token) {
for (int64_t i = 0; i < n_tokens_all; ++i) {
if (batch.token[i] < 0 || (uint32_t) batch.token[i] >= model.vocab.n_tokens()) {
LLAMA_LOG_ERROR("%s: invalid token[%" PRId64 "] = %d\n", __func__, i, batch.token[i]);
throw std::runtime_error("invalid token");
return -1;
}
if (batch.seq_id && (batch.seq_id[i][0] < 0 || batch.seq_id[i][0] >= LLAMA_MAX_PARALLEL_SEQUENCES)) {
LLAMA_LOG_ERROR("%s: invalid seq_id[%" PRId64 "] = %d >= %d\n", __func__, i, batch.seq_id[i][0], LLAMA_MAX_PARALLEL_SEQUENCES);
return -1;
}
}
}