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

Update vLLM Benchmark Suite for Xeon based on 0.9.2 release (#21486)

Browse Source 
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
This commit is contained in:
Louie Tsai
2025-07-29 22:57:03 -07:00
committed by GitHub
parent 4cd7fe6cea
commit 6f8d261882
5 changed files with 437 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
.buildkite/nightly-benchmarks/tests/serving-tests-cpu.json
View File

@@ -6,6 +6,7 @@
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
@@ -18,6 +19,8 @@
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"load_format": "dummy"
},
"client_parameters": {
@@ -36,6 +39,7 @@
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
@@ -48,6 +52,8 @@
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"load_format": "dummy"
},
"client_parameters": {
@@ -66,6 +72,7 @@
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
@@ -78,6 +85,8 @@
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"load_format": "dummy"
},
"client_parameters": {
@@ -96,6 +105,7 @@
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
@@ -109,6 +119,8 @@
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"load_format": "dummy"
},
"client_parameters": {
@@ -129,6 +141,7 @@
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
@@ -142,6 +155,8 @@
"disable_log_stats": "",
"disable_log_requests": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"load_format": "dummy"
},
"client_parameters": {