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

server: continuous performance monitoring and PR comment (#6283)

Browse source 
* server: bench: init

* server: bench: reduce list of GPU nodes

* server: bench: fix graph, fix output artifact

* ci: bench: add mermaid in case of image cannot be uploaded

* ci: bench: more resilient, more metrics

* ci: bench: trigger build

* ci: bench: fix duration

* ci: bench: fix typo

* ci: bench: fix mermaid values, markdown generated

* typo on the step name

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* ci: bench: trailing spaces

* ci: bench: move images in a details section

* ci: bench: reduce bullet point size

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Pierrick Hymbert 2024-03-27 20:26:49 +01:00 • committed by GitHub
parent 53c7ec53d5
commit a016026a3a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 603 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

19
examples/server/tests/features/steps/steps.py
View file

@ -1114,7 +1114,10 @@ def start_server_background(context):
server_args.append('--verbose')
if 'SERVER_LOG_FORMAT_JSON' not in os.environ:
server_args.extend(['--log-format', "text"])
print(f"starting server with: {context.server_path} {server_args}")
args = [str(arg) for arg in [context.server_path, *server_args]]
print(f"bench: starting server with: {' '.join(args)}")
flags = 0
if 'nt' == os.name:
flags |= subprocess.DETACHED_PROCESS
@ -1130,16 +1133,14 @@ def start_server_background(context):
[str(arg) for arg in [context.server_path, *server_args]],
**pkwargs)
def log_stdout(process):
for line in iter(process.stdout.readline, b''):
print(line.decode('utf-8'), end='')
thread_stdout = threading.Thread(target=log_stdout, args=(context.server_process,))
def server_log(in_stream, out_stream):
for line in iter(in_stream.readline, b''):
print(line.decode('utf-8'), end='', file=out_stream)
thread_stdout = threading.Thread(target=server_log, args=(context.server_process.stdout, sys.stdout))
thread_stdout.start()
def log_stderr(process):
for line in iter(process.stderr.readline, b''):
print(line.decode('utf-8'), end='', file=sys.stderr)
thread_stderr = threading.Thread(target=log_stderr, args=(context.server_process,))
thread_stderr = threading.Thread(target=server_log, args=(context.server_process.stderr, sys.stderr))
thread_stderr.start()
print(f"server pid={context.server_process.pid}, behave pid={os.getpid()}")