Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-02-02 15:02:47 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix restoring the number of outputs from state files (#6687)

Browse Source
This commit is contained in:
compilade 2024-04-15 08:56:55 -04:00 committed by GitHub
parent 3272896d79
commit 132f55795e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llama.cpp
View File

@ -15478,6 +15478,8 @@ size_t llama_state_set_data(struct llama_context * ctx, const uint8_t * src) {
GGML_ASSERT((uint32_t) id < ctx->cparams.n_batch);
ctx->output_ids[id] = i;
}
ctx->n_outputs = n_outputs;
}
}