Skip to content

server : fix mtmd checkpoints #16591

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 15, 2025
Merged

server : fix mtmd checkpoints #16591

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions tools/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3812,7 +3812,7 @@ struct server_context {
if (slot.n_past > 0 && slot.n_past < (int) slot.prompt.tokens.size()) {
const auto pos_min = llama_memory_seq_pos_min(llama_get_memory(ctx), slot.id);
if (pos_min == -1) {
SLT_ERR(slot, "n_past = %d, cache_tokens.size() = %d, seq_id = %d, pos_min = %d\n", slot.n_past, (int) slot.prompt.tokens.size(), slot.id, pos_min);
SLT_ERR(slot, "n_past = %d, slot.prompt.tokens.size() = %d, seq_id = %d, pos_min = %d\n", slot.n_past, (int) slot.prompt.tokens.size(), slot.id, pos_min);
GGML_ABORT("pos_min == -1, but n_past > 0 - should not happen: https://github.com/ggml-org/llama.cpp/pull/13833#discussion_r2116181237");
}

Expand Down Expand Up @@ -3860,7 +3860,7 @@ struct server_context {
}

if (pos_min > pos_min_thold) {
SLT_WRN(slot, "n_past = %d, cache_tokens.size() = %d, seq_id = %d, pos_min = %d, n_swa = %d\n", slot.n_past, (int) slot.prompt.tokens.size(), slot.id, pos_min, n_swa);
SLT_WRN(slot, "n_past = %d, slot.prompt.tokens.size() = %d, seq_id = %d, pos_min = %d, n_swa = %d\n", slot.n_past, (int) slot.prompt.tokens.size(), slot.id, pos_min, n_swa);

// search for a context checkpoint
const auto it = std::find_if(
Expand Down Expand Up @@ -4028,7 +4028,7 @@ struct server_context {
}
}

// SLT_INF(slot, "new cache_tokens: %s\n", slot.cache_tokens.str().c_str());
// SLT_INF(slot, "new slot.prompt.tokens: %s\n", slot.slot.prompt.tokens.str().c_str());

SLT_INF(slot, "prompt processing progress, n_past = %d, n_tokens = %d, progress = %f\n", slot.n_past, batch.n_tokens, (float) slot.n_past / slot.n_prompt_tokens());

Expand Down
5 changes: 3 additions & 2 deletions tools/server/utils.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1237,9 +1237,10 @@ struct server_tokens {
// allowed to resize ^ ^
// disallowed to resize ^ ^ ^
if (n > 0) {
llama_token last_token = tokens[n - 1];
// make sure we never remove tokens in the middle of an image
if (last_token == LLAMA_TOKEN_NULL) {
// note that the case where we keep a full image at the end is allowed:
// tokens[n - 1] == LLAMA_TOKEN_NULL && tokens[n] != LLAMA_TOKEN_NULL
if (tokens[n - 1] == LLAMA_TOKEN_NULL && tokens[n] == LLAMA_TOKEN_NULL) {
find_chunk(n - 1); // will throw an error if the token is not begin-of-chunk
}
}
Expand Down
Loading