Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "4fa7ce46f31cbd97b4651694caf9991cc395a259"
Unverified Commit 067c34a1 authored by Roger Wang's avatar Roger Wang Committed by GitHub
Browse files

docs: remove deprecated disable-log-requests flag (#22113) 


Signed-off-by: default avatarRoger Wang <hey@rogerw.me>
parent c64861d6
Hide whitespace changes
Inline Side-by-side
Showing with 14 additions and 41 deletions
.buildkite/scripts/tpu/run_bm.sh
View file @ 067c34a1
......@@ -44,7 +44,6 @@ echo
VLLM_USE_V1=1 vllm serve $MODEL \
--seed 42 \
--disable-log-requests \
--max-num-seqs $MAX_NUM_SEQS \
--max-num-batched-tokens $MAX_NUM_BATCHED_TOKENS \
--tensor-parallel-size $TENSOR_PARALLEL_SIZE \
......
benchmarks/README.md
View file @ 067c34a1
......@@ -91,7 +91,7 @@ become available.
First start serving your model
```bash
vllm serve NousResearch/Hermes-3-Llama-3.1-8B --disable-log-requests
vllm serve NousResearch/Hermes-3-Llama-3.1-8B
```
Then run the benchmarking script
......@@ -146,7 +146,7 @@ If the dataset you want to benchmark is not supported yet in vLLM, even then you
```bash
# start server
VLLM_USE_V1=1 vllm serve meta-llama/Llama-3.1-8B-Instruct --disable-log-requests
VLLM_USE_V1=1 vllm serve meta-llama/Llama-3.1-8B-Instruct
```
```bash
......@@ -171,7 +171,7 @@ You can skip applying chat template if your data already has it by using `--cust
```bash
# need a model with vision capability here
vllm serve Qwen/Qwen2-VL-7B-Instruct --disable-log-requests
vllm serve Qwen/Qwen2-VL-7B-Instruct
```
```bash
......@@ -205,7 +205,7 @@ vllm bench serve \
### Other HuggingFaceDataset Examples
```bash
vllm serve Qwen/Qwen2-VL-7B-Instruct --disable-log-requests
vllm serve Qwen/Qwen2-VL-7B-Instruct
```
`lmms-lab/LLaVA-OneVision-Data`:
......@@ -430,7 +430,7 @@ Benchmark the performance of structured output generation (JSON, grammar, regex)
### Server Setup
```bash
vllm serve NousResearch/Hermes-3-Llama-3.1-8B --disable-log-requests
vllm serve NousResearch/Hermes-3-Llama-3.1-8B
```
### JSON Schema Benchmark
......
benchmarks/auto_tune/auto_tune.sh
View file @ 067c34a1
......@@ -60,7 +60,6 @@ start_server() {
pkill -f vllm
VLLM_USE_V1=1 VLLM_SERVER_DEV_MODE=1 VLLM_TORCH_PROFILER_DIR=$profile_dir vllm serve $MODEL \
--disable-log-requests \
--port 8004 \
--gpu-memory-utilization $gpu_memory_utilization \
--max-num-seqs $max_num_seqs \
......
benchmarks/benchmark_serving.py
View file @ 067c34a1
......@@ -5,8 +5,7 @@ r"""Benchmark online serving throughput.
On the server side, run one of the following commands:
vLLM OpenAI API server
vllm serve <your_model> \
--swap-space 16 \
--disable-log-requests
--swap-space 16
On the client side, run:
python benchmarks/benchmark_serving.py \
......
benchmarks/benchmark_serving_structured_output.py
View file @ 067c34a1
......@@ -4,7 +4,7 @@ r"""Benchmark online serving throughput with structured outputs.
On the server side, run one of the following commands:
(vLLM OpenAI API server)
vllm serve <your_model> --disable-log-requests
vllm serve <your_model>
On the client side, run:
python benchmarks/benchmark_serving_structured_output.py \
......
docs/design/p2p_nccl_connector.md
View file @ 067c34a1
......@@ -109,7 +109,6 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
--max-num-seqs 256 \
--trust-remote-code \
--gpu-memory-utilization 0.9 \
--disable-log-request \
--kv-transfer-config \
'{"kv_connector":"P2pNcclConnector","kv_role":"kv_producer","kv_buffer_size":"1e1","kv_port":"21001","kv_connector_extra_config":{"proxy_ip":"10.0.1.1","proxy_port":"30001","http_port":"20001"}}' > /var/vllm.log 2>&1 &
```
......@@ -131,7 +130,6 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
--max-num-seqs 256 \
--trust-remote-code \
--gpu-memory-utilization 0.7 \
--disable-log-request \
--kv-transfer-config \
'{"kv_connector":"P2pNcclConnector","kv_role":"kv_consumer","kv_buffer_size":"8e9","kv_port":"22001","kv_connector_extra_config":{"proxy_ip":"10.0.1.1","proxy_port":"30001","http_port":"20002"}}' > /var/vllm.log 2>&1 &
```
......@@ -153,7 +151,6 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
--max-num-seqs 256 \
--trust-remote-code \
--gpu-memory-utilization 0.7 \
--disable-log-request \
--kv-transfer-config \
'{"kv_connector":"P2pNcclConnector","kv_role":"kv_consumer","kv_buffer_size":"8e9","kv_port":"23001","kv_connector_extra_config":{"proxy_ip":"10.0.1.1","proxy_port":"30001","http_port":"20003"}}' > /var/vllm.log 2>&1 &
```
......@@ -175,7 +172,6 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
--max-num-seqs 256 \
--trust-remote-code \
--gpu-memory-utilization 0.7 \
--disable-log-request \
--kv-transfer-config \
'{"kv_connector":"P2pNcclConnector","kv_role":"kv_consumer","kv_buffer_size":"8e9","kv_port":"24001","kv_connector_extra_config":{"proxy_ip":"10.0.1.1","proxy_port":"30001","http_port":"20004"}}' > /var/vllm.log 2>&1 &
```
......@@ -206,7 +202,6 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
--max-num-seqs 256 \
--trust-remote-code \
--gpu-memory-utilization 0.9 \
--disable-log-request \
--kv-transfer-config \
'{"kv_connector":"P2pNcclConnector","kv_role":"kv_producer","kv_buffer_size":"1e1","kv_port":"21001","kv_connector_extra_config":{"proxy_ip":"10.0.1.1","proxy_port":"30001","http_port":"20001"}}' > /var/vllm.log 2>&1 &
```
......@@ -228,7 +223,6 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
--max-num-seqs 256 \
--trust-remote-code \
--gpu-memory-utilization 0.9 \
--disable-log-request \
--kv-transfer-config \
'{"kv_connector":"P2pNcclConnector","kv_role":"kv_producer","kv_buffer_size":"1e1","kv_port":"22001","kv_connector_extra_config":{"proxy_ip":"10.0.1.1","proxy_port":"30001","http_port":"20002"}}' > /var/vllm.log 2>&1 &
```
......@@ -250,7 +244,6 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
--max-num-seqs 256 \
--trust-remote-code \
--gpu-memory-utilization 0.9 \
--disable-log-request \
--kv-transfer-config \
'{"kv_connector":"P2pNcclConnector","kv_role":"kv_producer","kv_buffer_size":"1e1","kv_port":"23001","kv_connector_extra_config":{"proxy_ip":"10.0.1.1","proxy_port":"30001","http_port":"20003"}}' > /var/vllm.log 2>&1 &
```
......@@ -272,7 +265,6 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
--max-num-seqs 256 \
--trust-remote-code \
--gpu-memory-utilization 0.7 \
--disable-log-request \
--kv-transfer-config \
'{"kv_connector":"P2pNcclConnector","kv_role":"kv_consumer","kv_buffer_size":"8e9","kv_port":"24001","kv_connector_extra_config":{"proxy_ip":"10.0.1.1","proxy_port":"30001","http_port":"20004"}}' > /var/vllm.log 2>&1 &
```
......
docs/models/supported_models.md
View file @ 067c34a1
......@@ -255,7 +255,7 @@ export https_proxy=http://your.proxy.server:port
https_proxy=http://your.proxy.server:port huggingface-cli download <model_name>
# or use vllm cmd directly
https_proxy=http://your.proxy.server:port vllm serve <model_name> --disable-log-requests
https_proxy=http://your.proxy.server:port vllm serve <model_name>
```
- Set the proxy in Python interpreter:
......
examples/online_serving/disaggregated_serving_p2p_nccl_xpyd/disagg_example_p2p_nccl_xpyd.sh
View file @ 067c34a1
......@@ -178,7 +178,6 @@ main() {
--max-num-seqs 256 \
--trust-remote-code \
--gpu-memory-utilization 0.9 \
--disable-log-request \
--kv-transfer-config \
"{\"kv_connector\":\"P2pNcclConnector\",\"kv_role\":\"kv_producer\",\"kv_buffer_size\":\"1e1\",\"kv_port\":\"$kv_port\",\"kv_connector_extra_config\":{\"proxy_ip\":\"0.0.0.0\",\"proxy_port\":\"$PROXY_PORT\",\"http_port\":\"$port\",\"send_type\":\"PUT_ASYNC\",\"nccl_num_channels\":\"16\"}}" > prefill$((i+1)).log 2>&1 &
PIDS+=($!)
......@@ -207,7 +206,6 @@ main() {
--max-num-seqs 256 \
--trust-remote-code \
--gpu-memory-utilization 0.7 \
--disable-log-request \
--kv-transfer-config \
"{\"kv_connector\":\"P2pNcclConnector\",\"kv_role\":\"kv_consumer\",\"kv_buffer_size\":\"8e9\",\"kv_port\":\"$kv_port\",\"kv_connector_extra_config\":{\"proxy_ip\":\"0.0.0.0\",\"proxy_port\":\"$PROXY_PORT\",\"http_port\":\"$port\",\"send_type\":\"PUT_ASYNC\",\"nccl_num_channels\":\"16\"}}" > decode$((i+1)).log 2>&1 &
PIDS+=($!)
......
examples/online_serving/prometheus_grafana/README.md
View file @ 067c34a1
......@@ -13,8 +13,7 @@ Prometheus metric logging is enabled by default in the OpenAI-compatible server.
```bash
vllm serve mistralai/Mistral-7B-v0.1 \
--max-model-len 2048 \
--disable-log-requests
--max-model-len 2048
```
Launch Prometheus and Grafana servers with `docker compose`:
......
examples/others/lmcache/disagg_prefill_lmcache_v1/disagg_vllm_launcher.sh
View file @ 067c34a1
......@@ -28,7 +28,6 @@ if [[ $1 == "prefiller" ]]; then
CUDA_VISIBLE_DEVICES=0 \
vllm serve $MODEL \
--port 8100 \
--disable-log-requests \
--enforce-eager \
--kv-transfer-config \
'{"kv_connector":"LMCacheConnectorV1","kv_role":"kv_producer","kv_connector_extra_config": {"discard_partial_chunks": false, "lmcache_rpc_port": "producer1"}}'
......@@ -46,7 +45,6 @@ elif [[ $1 == "decoder" ]]; then
CUDA_VISIBLE_DEVICES=1 \
vllm serve $MODEL \
--port 8200 \
--disable-log-requests \
--enforce-eager \
--kv-transfer-config \
'{"kv_connector":"LMCacheConnectorV1","kv_role":"kv_consumer","kv_connector_extra_config": {"discard_partial_chunks": false, "lmcache_rpc_port": "consumer1"}}'
......
tests/entrypoints/openai/correctness/test_lmeval.py
View file @ 067c34a1
......@@ -22,7 +22,7 @@ TASK = "gsm8k"
FILTER = "exact_match,strict-match"
RTOL = 0.03
EXPECTED_VALUE = 0.54
DEFAULT_ARGS = ["--max-model-len", "4096", "--disable-log-requests"]
DEFAULT_ARGS = ["--max-model-len", "4096"]
MORE_ARGS_LIST = [
[], # Default
["--enable-chunked-prefill"], # Chunked
......
tests/entrypoints/openai/test_chunked_prompt.py
View file @ 067c34a1
......@@ -26,8 +26,6 @@ def server():
"--enable-chunked-prefill",
"--max-num-batched-tokens",
"1000",
# large prompts create a lot of output
"--disable-log-requests",
]
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
......
tests/models/quantization/test_bitsandbytes.py
View file @ 067c34a1
......@@ -102,7 +102,6 @@ def test_load_tp_4bit_bnb_model(hf_runner, vllm_runner, example_prompts,
def test_load_pp_4bit_bnb_model(model_name, description) -> None:
common_args = [
"--disable-log-stats",
"--disable-log-requests",
"--dtype",
"bfloat16",
"--enable-prefix-caching",
......
tests/v1/kv_connector/nixl_integration/run_accuracy_test.sh
View file @ 067c34a1
......@@ -88,7 +88,6 @@ run_tests_for_model() {
BASE_CMD="CUDA_VISIBLE_DEVICES=$GPU_ID VLLM_NIXL_SIDE_CHANNEL_PORT=$SIDE_CHANNEL_PORT vllm serve $model_name \
--port $PORT \
--enforce-eager \
--disable-log-requests \
--gpu-memory-utilization 0.2 \
--tensor-parallel-size $PREFILLER_TP_SIZE \
--kv-transfer-config '{\"kv_connector\":\"NixlConnector\",\"kv_role\":\"kv_both\"}'"
......@@ -121,7 +120,6 @@ run_tests_for_model() {
BASE_CMD="CUDA_VISIBLE_DEVICES=$GPU_ID VLLM_NIXL_SIDE_CHANNEL_PORT=$SIDE_CHANNEL_PORT vllm serve $model_name \
--port $PORT \
--enforce-eager \
--disable-log-requests \
--gpu-memory-utilization 0.2 \
--tensor-parallel-size $DECODER_TP_SIZE \
--kv-transfer-config '{\"kv_connector\":\"NixlConnector\",\"kv_role\":\"kv_both\"}'"
......
tests/v1/kv_connector/nixl_integration/run_edge_case_test.sh
View file @ 067c34a1
......@@ -57,7 +57,6 @@ run_tests_for_model() {
BASE_CMD="CUDA_VISIBLE_DEVICES=0 VLLM_NIXL_SIDE_CHANNEL_PORT=5559 vllm serve $model_name \
--port $PREFILL_PORT \
--enforce-eager \
--disable-log-requests \
--gpu-memory-utilization 0.2 \
--kv-transfer-config '{\"kv_connector\":\"NixlConnector\",\"kv_role\":\"kv_both\"}'"
......@@ -76,7 +75,6 @@ run_tests_for_model() {
BASE_CMD="CUDA_VISIBLE_DEVICES=1 VLLM_NIXL_SIDE_CHANNEL_PORT=6000 vllm serve $model_name \
--port $DECODE_PORT \
--enforce-eager \
--disable-log-requests \
--gpu-memory-utilization 0.2 \
--kv-transfer-config '{\"kv_connector\":\"NixlConnector\",\"kv_role\":\"kv_both\"}'"
......
tests/v1/kv_connector/nixl_integration/run_tpu_disagg_accuracy_test.sh
View file @ 067c34a1
......@@ -63,7 +63,6 @@ launch_baseline() {
--seed 42 \
--block-size ${BLOCK_SIZE} \
--gpu-memory-utilization 0.5 \
--disable-log-requests \
--enforce-eager"
echo ${BASELINE_BASE_CMD}
ssh -tt ${BASELINE_HOST} "${BASELINE_BASE_CMD}" &
......@@ -87,7 +86,6 @@ launch_pd() {
--block-size ${BLOCK_SIZE} \
--enforce-eager \
--gpu-memory-utilization 0.5 \
--disable-log-requests \
--kv-transfer-config '{\"kv_connector\":\"NixlConnector\",\"kv_role\":\"kv_both\",\"kv_buffer_device\":\"cpu\"}'"
......@@ -106,7 +104,6 @@ launch_pd() {
--block-size ${BLOCK_SIZE} \
--enforce-eager \
--gpu-memory-utilization 0.5 \
--disable-log-requests \
--kv-transfer-config '{\"kv_connector\":\"NixlConnector\",\"kv_role\":\"kv_both\",\"kv_buffer_device\":\"cpu\"}'"
echo ${PREFILL_BASE_CMD}
......
tests/v1/kv_connector/nixl_integration/run_tpu_edge_case_test.sh
View file @ 067c34a1
......@@ -68,7 +68,6 @@ launch_pd() {
--block-size ${BLOCK_SIZE} \
--enforce-eager \
--gpu-memory-utilization 0.5 \
--disable-log-requests \
--kv-transfer-config '{\"kv_connector\":\"NixlConnector\",\"kv_role\":\"kv_both\",\"kv_buffer_device\":\"cpu\"}'"
......@@ -87,7 +86,6 @@ launch_pd() {
--block-size ${BLOCK_SIZE} \
--enforce-eager \
--gpu-memory-utilization 0.5 \
--disable-log-requests \
--kv-transfer-config '{\"kv_connector\":\"NixlConnector\",\"kv_role\":\"kv_both\",\"kv_buffer_device\":\"cpu\"}'"
echo ${PREFILL_BASE_CMD}
......
tests/v1/sample/test_logprobs_e2e.py
View file @ 067c34a1
......@@ -15,7 +15,7 @@ EXPECTED_VALUE = 0.62
MODEL = "meta-llama/Llama-3.2-1B-Instruct"
MODEL_ARGS = f"pretrained={MODEL},enforce_eager=True,enable_prefix_caching=False,gpu_memory_utilization=0.8" # noqa: E501
SERVER_ARGS = [
"--enforce_eager", "--no_enable_prefix_caching", "--disable-log-requests",
"--enforce_eager", "--no_enable_prefix_caching",
"--gpu-memory-utilization=0.8"
]
NUM_CONCURRENT = 100
......
vllm/utils/__init__.py
View file @ 067c34a1
......@@ -1673,8 +1673,9 @@ class FlexibleArgumentParser(ArgumentParser):
# Special case warning because the warning below won't trigger
# if –-disable-log-requests because its value is default.
logger.warning_once(
"argument '--disable-log-requests' is deprecated. This "
"will be removed in v0.12.0.")
"argument '--disable-log-requests' is deprecated and "
"replaced with '--enable-log-requests'. This will be "
"removed in v0.12.0.")
namespace, args = super().parse_known_args(args, namespace)
for action in FlexibleArgumentParser._deprecated:
if (hasattr(namespace, dest := action.dest)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment