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

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": {