biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc] Improve UX of --enable-log-requests (#35723)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-03-03 00:24:09 +08:00
committed by GitHub
parent 4034c3d32e
commit 792a74b973
5 changed files with 21 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
benchmarks/auto_tune/auto_tune.sh
View File

@@ -85,7 +85,6 @@ start_server() {
# Each argument and its value are separate elements. # Each argument and its value are separate elements.
local common_args_array=( local common_args_array=(
"$MODEL" "$MODEL"
"--disable-log-requests"
"--port" "8004" "--port" "8004"
"--host" "$HOSTNAME" "--host" "$HOSTNAME"
"--gpu-memory-utilization" "$gpu_memory_utilization" "--gpu-memory-utilization" "$gpu_memory_utilization"

2
benchmarks/multi_turn/README.md
View File

@@ -7,7 +7,7 @@ First start serving your model
```bash ```bash
export MODEL_PATH=/models/meta-llama/Meta-Llama-3.1-8B-Instruct/ export MODEL_PATH=/models/meta-llama/Meta-Llama-3.1-8B-Instruct/
vllm serve $MODEL_PATH --served-model-name Llama --disable-log-requests vllm serve $MODEL_PATH --served-model-name Llama
``` ```
The variable `MODEL_PATH` should be a path to the model files (e.g. downloaded from huggingface). The variable `MODEL_PATH` should be a path to the model files (e.g. downloaded from huggingface).

12
vllm/engine/arg_utils.py
View File

@@ -2187,14 +2187,10 @@ class AsyncEngineArgs(EngineArgs):
"--enable-log-requests", "--enable-log-requests",
action=argparse.BooleanOptionalAction, action=argparse.BooleanOptionalAction,
default=AsyncEngineArgs.enable_log_requests, default=AsyncEngineArgs.enable_log_requests,
help="Enable logging requests.", help="Enable logging request information, dependant on log level:\n"
) "- INFO: Request ID, parameters and LoRA request.\n"
parser.add_argument( "- DEBUG: Prompt inputs (e.g: text, token IDs).\n"
"--disable-log-requests", "You can set the minimum log level via `VLLM_LOGGING_LEVEL`.",
action=argparse.BooleanOptionalAction,
default=not AsyncEngineArgs.enable_log_requests,
help="[DEPRECATED] Disable logging requests.",
deprecated=True,
) )
current_platform.pre_register_and_update(parser) current_platform.pre_register_and_update(parser)
return parser return parser

14
vllm/entrypoints/logger.py
View File

@@ -18,6 +18,20 @@ class RequestLogger:
def __init__(self, *, max_log_len: int | None) -> None: def __init__(self, *, max_log_len: int | None) -> None:
self.max_log_len = max_log_len self.max_log_len = max_log_len
if not logger.isEnabledFor(logging.INFO):
logger.warning_once(
"`--enable-log-requests` is set but "
"the minimum log level is higher than INFO. "
"No request information will be logged."
)
elif not logger.isEnabledFor(logging.DEBUG):
logger.info_once(
"`--enable-log-requests` is set but "
"the minimum log level is higher than DEBUG. "
"Only limited information will be logged to minimize overhead. "
"To view more details, set `VLLM_LOGGING_LEVEL=DEBUG`."
)
def log_inputs( def log_inputs(
self, self,
request_id: str, request_id: str,

3
vllm/entrypoints/openai/cli_args.py
View File

@@ -143,7 +143,8 @@ class BaseFrontendArgs:
templates and other tokenizer configuration.""" templates and other tokenizer configuration."""
enable_log_outputs: bool = False enable_log_outputs: bool = False
"""If set to True, log model outputs (generations). """If set to True, log model outputs (generations).
Requires --enable-log-requests.""" Requires `--enable-log-requests`. As with `--enable-log-requests`,
information is only logged at INFO level at maximum."""
enable_log_deltas: bool = True enable_log_deltas: bool = True
"""If set to False, output deltas will not be logged. Relevant only if """If set to False, output deltas will not be logged. Relevant only if
--enable-log-outputs is set. --enable-log-outputs is set.