z3st/modelhub-submit-agent
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

fix: move gpu_num/cpu_num outside values block to match API spec

Browse Source
This commit is contained in:
z3st
2026-07-23 22:10:17 +08:00
parent 85c456afe0
commit 12bf6d637f
1 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
main.py
View File

@@ -262,8 +262,8 @@ def build_config_params(gpu: str) -> str:
'max_model_len': 4096, 'max_model_len': 4096,
'modelFormat': 'GGUF', 'modelFormat': 'GGUF',
'sut_config': { 'sut_config': {
'values': {
'gpu_num': 1, 'gpu_num': 1,
'values': {
'command': [ 'command': [
'/bin/bash', '-ic', '/bin/bash', '-ic',
'llama-server --model /model --alias llm --threads 20 ' 'llama-server --model /model --alias llm --threads 20 '
@@ -273,8 +273,9 @@ def build_config_params(gpu: str) -> str:
} }
}, },
'ref_config': { 'ref_config': {
'gpu_num': 1,
'values': { 'values': {
'cpu_num': 2, 'gpu_num': 1, 'cpu_num': 2,
'command': [ 'command': [
'llama-server', '--model', '/model', '--alias', 'llm', 'llama-server', '--model', '/model', '--alias', 'llm',
'--threads', '20', '--n-gpu-layers', '999', '--threads', '20', '--n-gpu-layers', '999',
@@ -298,8 +299,8 @@ def build_config_params(gpu: str) -> str:
'max_model_len': 2048, 'max_model_len': 2048,
'modelFormat': 'HuggingFace', 'modelFormat': 'HuggingFace',
'sut_config': { 'sut_config': {
'values': {
'gpu_num': 1, 'gpu_num': 1,
'values': {
'command': [ 'command': [
'/bin/bash', '-ic', '/bin/bash', '-ic',
'vllm serve /model --port 8000 --served-model-name llm --max-model-len 2048 --dtype auto --gpu-memory-utilization 0.95 -tp 1 --enforce-eager --trust-remote-code' 'vllm serve /model --port 8000 --served-model-name llm --max-model-len 2048 --dtype auto --gpu-memory-utilization 0.95 -tp 1 --enforce-eager --trust-remote-code'
@@ -307,8 +308,9 @@ def build_config_params(gpu: str) -> str:
} }
}, },
'ref_config': { 'ref_config': {
'gpu_num': 1,
'values': { 'values': {
'cpu_num': 2, 'gpu_num': 1, 'cpu_num': 2,
'command': [ 'command': [
'vllm', 'serve', '/model', '--port', '8000', 'vllm', 'serve', '/model', '--port', '8000',
'--served-model-name', 'llm', '--max-model-len', '2048', '--served-model-name', 'llm', '--max-model-len', '2048',