mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 33 Packages Projects Releases Wiki Activity

server : support multi-modal context checkpoints (#19849)

Browse Source 
* Modify llama-memory-hybrid-iswa.cpp

* Modify llama-memory-recurrent.cpp

* Modify server-common.cpp

* Modify server-common.h

* Modify server-context.cpp

* Modify server-task.h

* Added comment to llama-memory-hybrid-iswa.cpp

* Remove comment from server-context.cpp

* Stylistic fix server-context.cpp

* Fix an issue when seqrm isn't called in server-context.cpp

* cont : alternative impl

* cont : cleanup

* cont : n_tokens -> int64_t

---------

Co-authored-by: timkhronos <timkhronos@gmail.com>
This commit is contained in:
Georgi Gerganov
2026-02-25 15:14:27 +02:00
committed by GitHub
parent c747294b2d
commit d7d826b3c1
5 changed files with 100 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-memory-recurrent.cpp
+1 -1
View File
@@ -163,7 +163,7 @@ bool llama_memory_recurrent::seq_rm(llama_seq_id seq_id, llama_pos p0, llama_pos
const auto & cell = cells[tail_id];
// partial intersection is invalid if it includes the final pos
if (0 < p0 && p0 <= cell.pos && p1 > cell.pos) {
//printf("[DEBUG] inside `llama_memory_recurrent::seq_rm`: partial intersection is invalid, so returning false\n");
//printf("[DEBUG] inside `llama_memory_recurrent::seq_rm`: partial intersection is invalid, so returning false, p0 = %d, cell.pos = %d, p1 = %d\n", p0, cell.pos, p1);
return false;
}
// invalidate tails which will be cleared