CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +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

7
include/llama.h
View File

@@ -543,6 +543,9 @@ extern "C" {
// Returns true if the model is recurrent (like Mamba, RWKV, etc.)
LLAMA_API bool llama_model_is_recurrent(const struct llama_model * model);
// Returns true if the model is hybrid (like Jamba, Granite, etc.)
LLAMA_API bool llama_model_is_hybrid(const struct llama_model * model);
// Returns true if the model is diffusion-based (like LLaDA, Dream, etc.)
LLAMA_API bool llama_model_is_diffusion(const struct llama_model * model);
@@ -791,8 +794,12 @@ extern "C" {
size_t n_token_capacity,
size_t * n_token_count_out);
// for backwards-compat
#define LLAMA_STATE_SEQ_FLAGS_SWA_ONLY 1
// work only with partial states, such as SWA KV cache or recurrent cache (e.g. Mamba)
#define LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY 1
typedef uint32_t llama_state_seq_flags;
LLAMA_API size_t llama_state_seq_get_size_ext(