From 2002bc96bf2cbf5ab981a17d7e994d817c9801f5 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Thu, 7 Mar 2024 11:41:53 +0200 Subject: server : refactor (#5882) * server : refactoring (wip) * server : remove llava/clip objects from build * server : fix empty prompt handling + all slots idle logic * server : normalize id vars * server : code style * server : simplify model chat template validation * server : code style * server : minor * llama : llama_chat_apply_template support null buf * server : do not process embedding requests when disabled * server : reorganize structs and enums + naming fixes * server : merge oai.hpp in utils.hpp * server : refactor system prompt update at start * server : disable cached prompts with self-extend * server : do not process more than n_batch tokens per iter * server: tests: embeddings use a real embeddings model (#5908) * server, tests : bump batch to fit 1 embedding prompt * server: tests: embeddings fix build type Debug is randomly failing (#5911) * server: tests: embeddings, use different KV Cache size * server: tests: embeddings, fixed prompt do not exceed n_batch, increase embedding timeout, reduce number of concurrent embeddings * server: tests: embeddings, no need to wait for server idle as it can timout * server: refactor: clean up http code (#5912) * server : avoid n_available var ggml-ci * server: refactor: better http codes * server : simplify json parsing + add comment about t_last * server : rename server structs * server : allow to override FQDN in tests ggml-ci * server : add comments --------- Co-authored-by: Pierrick Hymbert --- examples/server-embd.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'examples/server-embd.py') diff --git a/examples/server-embd.py b/examples/server-embd.py index c5c4ea87..118e0427 100644 --- a/examples/server-embd.py +++ b/examples/server-embd.py @@ -13,7 +13,7 @@ async def main(): model_url = "http://127.0.0.1:6900" responses: list[requests.Response] = await asyncio.gather(*[requests_post_async( url= f"{model_url}/embedding", - json= {"content": str(i)*1024} + json= {"content": str(0)*1024} ) for i in range(n)]) for response in responses: -- cgit v1.2.3