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

Deprecate --disable-log-requests and replace with --enable-log-requests (#21739)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-08-01 17:16:37 +01:00
committed by GitHub
parent 97608dc276
commit 2d7b09b998
18 changed files with 97 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.buildkite/nightly-benchmarks/tests/genai-perf-tests.json
View File

@@ -11,7 +11,6 @@
},
"vllm_server_parameters": {
"disable_log_stats": "",
"disable_log_requests": "",
"gpu_memory_utilization": 0.9,
"num_scheduler_steps": 10,
"max_num_seqs": 512,

6
.buildkite/nightly-benchmarks/tests/nightly-tests.json
View File

@@ -35,7 +35,6 @@
},
"vllm_server_parameters": {
"disable_log_stats": "",
"disable_log_requests": "",
"gpu_memory_utilization": 0.9,
"num_scheduler_steps": 10,
"max_num_seqs": 512,
@@ -90,7 +89,6 @@
},
"vllm_server_parameters": {
"disable_log_stats": "",
"disable_log_requests": "",
"gpu_memory_utilization": 0.9,
"num_scheduler_steps": 10,
"max_num_seqs": 512,
@@ -145,7 +143,6 @@
},
"vllm_server_parameters": {
"disable_log_stats": "",
"disable_log_requests": "",
"gpu_memory_utilization": 0.9,
"num_scheduler_steps": 10,
"max_num_seqs": 512,
@@ -197,7 +194,6 @@
},
"vllm_server_parameters": {
"disable_log_stats": "",
"disable_log_requests": "",
"gpu_memory_utilization": 0.9,
"num_scheduler_steps": 10,
"max_num_seqs": 512,
@@ -251,7 +247,6 @@
},
"vllm_server_parameters": {
"disable_log_stats": "",
"disable_log_requests": "",
"gpu_memory_utilization": 0.9,
"num_scheduler_steps": 10,
"max_num_seqs": 512,
@@ -305,7 +300,6 @@
},
"vllm_server_parameters": {
"disable_log_stats": "",
"disable_log_requests": "",
"gpu_memory_utilization": 0.9,
"num_scheduler_steps": 10,
"max_num_seqs": 512,

6
.buildkite/nightly-benchmarks/tests/serving-tests-cpu-snc2.json
View File

@@ -17,7 +17,6 @@
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -50,7 +49,6 @@
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -83,7 +81,6 @@
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -117,7 +114,6 @@
"trust_remote_code": "",
"enable_chunked_prefill": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -153,7 +149,6 @@
"trust_remote_code": "",
"enable_chunked_prefill": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -189,7 +184,6 @@
"trust_remote_code": "",
"enable_chunked_prefill": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,

6
.buildkite/nightly-benchmarks/tests/serving-tests-cpu-snc3.json
View File

@@ -17,7 +17,6 @@
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -50,7 +49,6 @@
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -84,7 +82,6 @@
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -118,7 +115,6 @@
"trust_remote_code": "",
"enable_chunked_prefill": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -154,7 +150,6 @@
"trust_remote_code": "",
"enable_chunked_prefill": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -191,7 +186,6 @@
"trust_remote_code": "",
"enable_chunked_prefill": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,

5
.buildkite/nightly-benchmarks/tests/serving-tests-cpu.json
View File

@@ -17,7 +17,6 @@
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -50,7 +49,6 @@
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -83,7 +81,6 @@
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -117,7 +114,6 @@
"trust_remote_code": "",
"enable_chunked_prefill": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
@@ -153,7 +149,6 @@
"trust_remote_code": "",
"enable_chunked_prefill": "",
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,

6
.buildkite/nightly-benchmarks/tests/serving-tests.json
View File

@@ -7,7 +7,6 @@
"tensor_parallel_size": 1,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy"
},
"client_parameters": {
@@ -26,7 +25,6 @@
"tensor_parallel_size": 4,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy"
},
"client_parameters": {
@@ -45,7 +43,6 @@
"tensor_parallel_size": 2,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy"
},
"client_parameters": {
@@ -60,8 +57,7 @@
"test_name": "serving_llama70B_tp4_sharegpt_specdecode",
"qps_list": [2],
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"disable_log_requests": "",
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"swap_space": 16,
"speculative_config": {