haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

server: tests - slow inference causes timeout on the CI (#5715)

Browse source 
* server: tests - longer inference timeout for CI
This commit is contained in:
Pierrick Hymbert 2024-02-25 22:48:33 +01:00 committed by GitHub
parent 8b350356b2
commit e3965cf35a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 4 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
common/sampling.cpp
View file

@ -266,7 +266,7 @@ static llama_token llama_sampling_sample_impl(
// }
//}
LOG("sampled token: %5d: '%s'\n", id, llama_token_to_piece(ctx_main, id).c_str());
//LOG("sampled token: %5d: '%s'\n", id, llama_token_to_piece(ctx_main, id).c_str());
}
}

4
examples/server/tests/features/steps/steps.py
View file

@ -699,6 +699,8 @@ async def wait_for_health_status(context,
if context.debug:
print(f"Starting checking for health for expected_health_status={expected_health_status}")
timeout = 3 # seconds
if expected_health_status == 'ok':
timeout = 10 # CI slow inference
interval = 0.5
counter = 0
async with aiohttp.ClientSession() as session:
@ -736,7 +738,7 @@ async def wait_for_health_status(context,
if n_completions > 0:
return
assert False, 'timeout exceeded'
assert False, f'{expected_health_status} timeout exceeded {counter}s>={timeout}'
def assert_embeddings(embeddings):