vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	CMakeLists.txt
#	examples/simple-chat/simple-chat.cpp
#	src/llama-quant.cpp
#	tools/run/run.cpp
#	tools/server/README.md
This commit is contained in:
Concedo 2025-06-24 23:06:16 +08:00
commit ace537d44e
17 changed files with 554 additions and 212 deletions
Download patch file Download diff file Expand all files Collapse all files

26
src/llama-batch.cpp
View file

@ -244,22 +244,34 @@ bool llama_batch_allocr::init(
continue;
}
if (memory) {
const llama_pos p0 = memory ? memory->seq_pos_max(s) : -1;
if (p0 >= 0) {
bool ok = true;
if (batch.token) {
if (seq_pos_min(s) != memory->seq_pos_max(s) + 1) {
LLAMA_LOG_ERROR("%s: sequence %d does not start from the last position stored in the memory\n", __func__, s);
return false;
if (seq_pos_min(s) != p0 + 1) {
ok = false;
}
} else {
assert(batch.embd);
// for embeddings (typically used as vision input), we allow them to have repeating positions
// ref: https://github.com/ggml-org/llama.cpp/issues/13694#issuecomment-2983871762
if (seq_pos_min(s) != memory->seq_pos_max(s) && seq_pos_min(s) != memory->seq_pos_max(s) + 1) {
LLAMA_LOG_ERROR("%s: sequence %d does not start from the last position stored in the memory\n", __func__, s);
return false;
if (seq_pos_min(s) != p0 && seq_pos_min(s) != p0 + 1) {
ok = false;
}
}
if (!ok) {
LLAMA_LOG_ERROR(
"%s: the tokens of sequence %d in the input batch have inconsistent sequence positions:\n"
" - the last position stored in the memory module of the context (i.e. the KV cache) for sequence %d is X = %d\n"
" - the tokens for sequence %d in the input batch have a starting position of Y = %d\n"
" it is required that the sequence positions remain consecutive: Y = X + 1\n",
__func__, s, s, p0, s, seq_pos_min(s));
return false;
}
}
if (seq_pos_max(s) - seq_pos_min(s) + 1 > (int) seq_pos[s].size()) {