root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 02:14:35 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

server : update /props with "total_slots" value (#5373)

Browse Source 
* include total "num_slots" in default_generation_settings_for_props

* cleanup total_slots return value in /props endpoint

* update /props endpoint docs with total_slots

* remove num_slots from default_generation_settings_for_props

* update /props endpoint section
This commit is contained in:
Justin Parker 2024-02-07 01:15:19 -05:00 committed by GitHub
parent f68664ac24
commit f3e2b4fa3f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/README.md
View File

@ -276,13 +276,15 @@ Notice that each `probs` is an array of length `n_probs`.
{
"assistant_name": "",
"user_name": "",
"default_generation_settings": { ... }
"default_generation_settings": { ... },
"total_slots": 1
}
```
- `assistant_name` - the required assistant name to generate the prompt in case you have specified a system prompt for all slots.
- `user_name` - the required anti-prompt to generate the prompt in case you have specified a system prompt for all slots.
- `default_generation_settings` - the default generation settings for the `/completion` endpoint, has the same fields as the `generation_settings` response object from the `/completion` endpoint.
- `total_slots` - the total number of slots for process requests (defined by `--parallel` option)
- **POST** `/v1/chat/completions`: OpenAI-compatible Chat Completions API. Given a ChatML-formatted json description in `messages`, it returns the predicted completion. Both synchronous and streaming mode are supported, so scripted and interactive applications work fine. While no strong claims of compatibility with OpenAI API spec is being made, in our experience it suffices to support many apps. Only ChatML-tuned models, such as Dolphin, OpenOrca, OpenHermes, OpenChat-3.5, etc can be used with this endpoint. Compared to `api_like_OAI.py` this API implementation does not require a wrapper to be served.

4
examples/server/server.cpp
View File

@ -432,7 +432,6 @@ struct llama_server_context
}
default_generation_settings_for_props = get_formated_generation(slots.front());
default_generation_settings_for_props["num_slots"] = params.n_parallel;
default_generation_settings_for_props["seed"] = -1;
batch = llama_batch_init(n_ctx, 0, params.n_parallel);
@ -2639,7 +2638,8 @@ int main(int argc, char **argv)
json data = {
{ "user_name", llama.name_user.c_str() },
{ "assistant_name", llama.name_assistant.c_str() },
{ "default_generation_settings", llama.default_generation_settings_for_props }
{ "default_generation_settings", llama.default_generation_settings_for_props },
{ "total_slots", llama.params.n_parallel }
};
res.set_content(data.dump(), "application/json; charset=utf-8");
});