Compare commits

..

3 Commits

Author SHA1 Message Date
Mikhail Yevchenko d0347b0755 Update log file path and enhance load log messages 2026-05-18 18:41:14 +00:00
Lucas Armand 9bc9ba11c5 Increase TGI benchmark tokens to 500 2026-04-30 14:04:39 -07:00
LucasArmandVast 48fdc65e3d Update to vastai package (#84) 2026-04-14 10:41:31 -07:00
2 changed files with 4 additions and 2 deletions
+3 -1
View File
@@ -7,12 +7,14 @@ from vastai import Worker, WorkerConfig, HandlerConfig, LogActionConfig, Benchma
# vLLM model configuration
MODEL_SERVER_URL = 'http://127.0.0.1'
MODEL_SERVER_PORT = 18000
MODEL_LOG_FILE = '/var/log/portal/vllm.log'
MODEL_LOG_FILE = '/var/log/onstart.log'
MODEL_HEALTHCHECK_ENDPOINT = "/health"
# vLLM-specific log messages
MODEL_LOAD_LOG_MSG = [
"Application startup complete.",
"llama runner started in",
"Server listening on",
]
MODEL_ERROR_LOG_MSGS = [
+1 -1
View File
@@ -35,7 +35,7 @@ def benchmark_generator() -> dict:
benchmark_data = {
"inputs": prompt,
"parameters": {
"max_new_tokens": 128,
"max_new_tokens": 500,
"temperature": 0.7,
"return_full_text": False
}