nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

kv-cache: Fix state restore fragmented cache (#17982)

Browse Source 
* kv-cache : fix state restore with fragmented cache (#17527)

Change find_slot to allow non-contiguous allocation during state restore. Fixes 'failed to find available cells in kv cache' error when restoring state to fragmented cache.

* tests : update logic

* cleanup: tightened state_read_meta sig, added is_contiguous case

* fix: state_read_meta arg reorder loose ends

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
ssweens
2025-12-15 19:28:35 +02:00
committed by GitHub
co-authored by Georgi Gerganov
parent 0f4f35e7be
commit 4529c660c8
4 changed files with 213 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-kv-cache.h
+19 -2
View File
@@ -72,6 +72,23 @@ public:
void clear() {
idxs.clear();
}
// check if indices are contiguous starting from head()
bool is_contiguous() const {
if (idxs.empty() || idxs[0].empty()) {
return true;
}
if (idxs.size() > 1) {
return false;
}
const uint32_t h = idxs[0][0];
for (size_t i = 0; i < idxs[0].size(); ++i) {
if (idxs[0][i] != h + i) {
return false;
}
}
return true;
}
};
using slot_info_vec_t = std::vector<slot_info>;
@@ -264,8 +281,8 @@ private:
void state_write_meta(llama_io_write_i & io, const cell_ranges_t & cr, llama_seq_id seq_id = -1) const;
void state_write_data(llama_io_write_i & io, const cell_ranges_t & cr) const;
bool state_read_meta(llama_io_read_i & io, uint32_t strm, uint32_t cell_count, llama_seq_id dest_seq_id = -1);
bool state_read_data(llama_io_read_i & io, uint32_t strm, uint32_t cell_count);
bool state_read_meta(llama_io_read_i & io, uint32_t strm, uint32_t cell_count, slot_info & sinfo, llama_seq_id dest_seq_id = -1);
bool state_read_data(llama_io_read_i & io, uint32_t strm, uint32_t cell_count, const slot_info & sinfo);
};
class llama_kv_cache_context : public llama_memory_context_i {