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

[V0 Deprecation] Remove unused swap_space parameter (#36216)

Browse Source 
Signed-off-by: majiayu000 <1835304752@qq.com>
Co-authored-by: mcelrath
This commit is contained in:
lif
2026-03-07 22:09:55 +08:00
committed by GitHub
parent ee8a29511f
commit 00b814ba5a
22 changed files with 19 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.buildkite/performance-benchmarks/README.md
View File

@@ -83,7 +83,6 @@ We test the throughput by using `vllm bench serve` with request rate = inf to co
"server_parameters": {
"model": "meta-llama/Meta-Llama-3-8B",
"tensor_parallel_size": 1,
"swap_space": 16,
"disable_log_stats": "",
"load_format": "dummy"
},

4
.buildkite/performance-benchmarks/tests/serving-tests-hpu.json
View File

@@ -10,7 +10,6 @@
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"swap_space": 16,
"disable_log_stats": "",
"load_format": "dummy",
"max-model-len": 2048,
@@ -37,7 +36,6 @@
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"swap_space": 16,
"disable_log_stats": "",
"load_format": "dummy",
"max-model-len": 2048,
@@ -64,7 +62,6 @@
"server_parameters": {
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"tensor_parallel_size": 2,
"swap_space": 16,
"disable_log_stats": "",
"load_format": "dummy",
"max-model-len": 2048,
@@ -91,7 +88,6 @@
"server_parameters": {
"model": "deepseek-ai/DeepSeek-R1",
"tensor_parallel_size": 8,
"swap_space": 16,
"disable_log_stats": "",
"load_format": "dummy",
"max-model-len": 2048,

4
.buildkite/performance-benchmarks/tests/serving-tests.json
View File

@@ -5,7 +5,6 @@
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"swap_space": 16,
"disable_log_stats": "",
"load_format": "dummy"
},
@@ -23,7 +22,6 @@
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"swap_space": 16,
"disable_log_stats": "",
"load_format": "dummy"
},
@@ -41,7 +39,6 @@
"server_parameters": {
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"tensor_parallel_size": 2,
"swap_space": 16,
"disable_log_stats": "",
"load_format": "dummy"
},
@@ -59,7 +56,6 @@
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"swap_space": 16,
"speculative_config": {
"model": "turboderp/Qwama-0.5B-Instruct",
"num_speculative_tokens": 4,