xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-29 19:57:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

remove enforce-eager according to feedback.

Browse Source 
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
This commit is contained in:
Tsai, Louie 2025-12-24 10:44:05 -08:00
parent b00fd3592e
commit ff80f1427a
1 changed files with 18 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
.buildkite/performance-benchmarks/tests/serving-tests-cpu.json
View File

@ -33,8 +33,7 @@
{
"test_name": "serving_llama8B_tp1_sharegpt",
"server_parameters": {
"tensor_parallel_size": 1,
"enforce_eager": ""
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "sharegpt",
@ -44,8 +43,7 @@
{
"test_name": "serving_llama8B_tp2_sharegpt",
"server_parameters": {
"tensor_parallel_size": 2,
"enforce_eager": ""
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "sharegpt",
@ -55,8 +53,7 @@
{
"test_name": "serving_llama8B_tp1_random_128_128",
"server_parameters": {
"tensor_parallel_size": 1,
"enforce_eager": ""
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
@ -67,8 +64,7 @@
{
"test_name": "serving_llama8B_tp2_random_128_128",
"server_parameters": {
"tensor_parallel_size": 2,
"enforce_eager": ""
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
@ -79,8 +75,7 @@
{
"test_name": "serving_llama8B_tp4_random_128_128",
"server_parameters": {
"tensor_parallel_size": 4,
"enforce_eager": ""
"tensor_parallel_size": 4
},
"client_parameters": {
"dataset_name": "random",
@ -91,8 +86,7 @@
{
"test_name": "serving_llama8B_tp1_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 1,
"enforce_eager": ""
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
@ -103,8 +97,7 @@
{
"test_name": "serving_llama8B_tp2_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 2,
"enforce_eager": ""
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
@ -115,8 +108,7 @@
{
"test_name": "serving_llama8B_tp4_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 4,
"enforce_eager": ""
"tensor_parallel_size": 4
},
"client_parameters": {
"dataset_name": "random",
@ -127,8 +119,7 @@
{
"test_name": "serving_llama8B_tp1_random_2048_128",
"server_parameters": {
"tensor_parallel_size": 1,
"enforce_eager": ""
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
@ -139,8 +130,7 @@
{
"test_name": "serving_llama8B_tp2_random_2048_128",
"server_parameters": {
"tensor_parallel_size": 2,
"enforce_eager": ""
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
@ -151,8 +141,7 @@
{
"test_name": "serving_llama8B_tp4_random_2048_128",
"server_parameters": {
"tensor_parallel_size": 4,
"enforce_eager": ""
"tensor_parallel_size": 4
},
"client_parameters": {
"dataset_name": "random",
@ -203,8 +192,7 @@
"test_name": "serving_llama3B_tp1_random_128_128",
"server_parameters": {
"model": "meta-llama/Llama-3.2-3B-Instruct",
"tensor_parallel_size": 1,
"enforce_eager": ""
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "meta-llama/Llama-3.2-3B-Instruct",
@ -217,8 +205,7 @@
"test_name": "serving_granite2B_tp1_random_128_128",
"server_parameters": {
"model": "ibm-granite/granite-3.2-2b-instruct",
"tensor_parallel_size": 1,
"enforce_eager": ""
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "ibm-granite/granite-3.2-2b-instruct",
@ -231,8 +218,7 @@
"test_name": "serving_qwen1.7B_tp1_random_128_128",
"server_parameters": {
"model": "Qwen/Qwen3-1.7B",
"tensor_parallel_size": 1,
"enforce_eager": ""
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "Qwen/Qwen3-1.7B",
@ -245,8 +231,7 @@
"test_name": "serving_qwen4B_tp1_random_128_128",
"server_parameters": {
"model": "Qwen/Qwen3-4B",
"tensor_parallel_size": 1,
"enforce_eager": ""
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "Qwen/Qwen3-4B",
@ -259,8 +244,7 @@
"test_name": "serving_qwen8B_tp1_random_128_128",
"server_parameters": {
"model": "Qwen/Qwen3-8B",
"tensor_parallel_size": 1,
"enforce_eager": ""
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "Qwen/Qwen3-8B",
@ -273,8 +257,7 @@
"test_name": "serving_glm9B_tp1_random_128_128",
"server_parameters": {
"model": "zai-org/glm-4-9b-hf",
"tensor_parallel_size": 1,
"enforce_eager": ""
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "zai-org/glm-4-9b-hf",
@ -287,8 +270,7 @@
"test_name": "serving_gemma7B_tp1_random_128_128",
"server_parameters": {
"model": "google/gemma-7b",
"tensor_parallel_size": 1,
"enforce_eager": ""
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "google/gemma-7b",