CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : context checkpointing for hybrid and recurrent models (#16382)

Browse Source 
* initial commit for branch 3

* generalize `swa_checkpoint` to `ctx_checkpoint`

this extends `llama-server`'s SWA checkpointing logic to include
hybrid/recurrent models such as Jamba, Granite

* oops

* disable debug prints

* keep backwards compat with `--swa-checkpoints`

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* update prompt re-processing message

* fix off-by-one error per GG

* keep `seq_rm` log per GG

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* server : fix checkpoint logic to support recurrent caches

* server : cleanup and fixes

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
ddh0
2025-10-03 13:34:51 -05:00
committed by GitHub
parent 606a73f531
commit f6dcda3900
8 changed files with 87 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-kv-cache-iswa.cpp
View File

@@ -220,7 +220,7 @@ bool llama_kv_cache_iswa::get_can_shift() const {
}
void llama_kv_cache_iswa::state_write(llama_io_write_i & io, llama_seq_id seq_id, llama_state_seq_flags flags) const {
if ((flags & LLAMA_STATE_SEQ_FLAGS_SWA_ONLY) == 0) {
if ((flags & LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY) == 0) {
kv_base->state_write(io, seq_id, flags);
}
@@ -228,7 +228,7 @@ void llama_kv_cache_iswa::state_write(llama_io_write_i & io, llama_seq_id seq_id
}
void llama_kv_cache_iswa::state_read(llama_io_read_i & io, llama_seq_id seq_id, llama_state_seq_flags flags) {
if ((flags & LLAMA_STATE_SEQ_FLAGS_SWA_ONLY) == 0) {
if ((flags & LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY) == 0) {
kv_base->state_read(io, seq_id, flags);
}