mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-19 17:24:57 +02:00
Merge remote-tracking branch 'upstream/master' into xsn/server_docker_isolate
This commit is contained in:
@@ -133,7 +133,10 @@ class ServerProcess:
|
||||
self.external_server = "DEBUG_EXTERNAL" in os.environ
|
||||
|
||||
def start(self, timeout_seconds: int = DEFAULT_HTTP_TIMEOUT) -> None:
|
||||
env = {**os.environ}
|
||||
env = {
|
||||
**os.environ,
|
||||
"LLAMA_SERVER_DEBUG_FAKE_TIMING": "1",
|
||||
}
|
||||
if "LLAMA_CACHE" not in os.environ:
|
||||
env["LLAMA_CACHE"] = "tmp"
|
||||
if self.external_server:
|
||||
@@ -306,6 +309,7 @@ class ServerProcess:
|
||||
|
||||
# wait for server to start
|
||||
start_time = time.time()
|
||||
last_print_time = start_time
|
||||
while time.time() - start_time < timeout_seconds:
|
||||
try:
|
||||
response = self.make_request("GET", "/health", headers={
|
||||
@@ -320,8 +324,10 @@ class ServerProcess:
|
||||
if self.process.poll() is not None:
|
||||
raise RuntimeError(f"Server process died with return code {self.process.returncode}")
|
||||
|
||||
print(f"Waiting for server to start...")
|
||||
time.sleep(0.5)
|
||||
if time.time() - last_print_time >= 1.0:
|
||||
print(f"Waiting for server to start...")
|
||||
last_print_time = time.time()
|
||||
time.sleep(0.01)
|
||||
raise TimeoutError(f"Server did not start within {timeout_seconds} seconds")
|
||||
|
||||
def stop(self) -> None:
|
||||
|
||||
Reference in New Issue
Block a user