happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

examples : set n_seq_max = 2 for ctx3 

This commit updates the save-load-state example to set the n_seq_max
parameter to 2 when initializing the ctx3 context.

The motivation for this change is that using 1 as n_parallel/n_seq_max
the context only supports one sequence, but the test laster tries to
use a second sequence which results in the following error:
```console
main : loaded state with 4 tokens
main : seq 0 copied, 225760 bytes
main : kv cache cleared
find_slot: seq_id=1 >= n_seq_max=1 Try using a bigger --parallel value
state_read_meta: failed to find available cells in kv cache
```
This seems to only happen for recurrent/hybrid models.
This commit is contained in:
Daniel Bevenius 2026-02-06 13:15:20 +01:00
parent 61693b5bda
commit 6693df846c
No known key found for this signature in database
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/save-load-state/save-load-state.cpp
View File

@ -151,7 +151,9 @@ int main(int argc, char ** argv) {
}
// make new context
llama_context * ctx3 = llama_init_from_model(model, common_context_params_to_llama(params));
auto params_ctx3 = common_context_params_to_llama(params);
params_ctx3.n_seq_max = 2;
llama_context * ctx3 = llama_init_from_model(model, params_ctx3);
llama_sampler * smpl3 = llama_sampler_chain_init(sparams);