Mathis/llamactl
1
0
Fork 0
mirror of https://github.com/lordmathis/llamactl.git synced 2025-11-06 00:54:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix vllm command parsing

Browse Source
This commit is contained in:
Matúš Námešný
2025-09-22 21:25:50 +02:00
parent 313666ea17
commit 184d6df1bc
2 changed files with 34 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
pkg/backends/vllm/vllm_test.go
View File

@@ -14,17 +14,22 @@ func TestParseVllmCommand(t *testing.T) {
}{
{
name: "basic vllm serve command",
command: "vllm serve --model microsoft/DialoGPT-medium",
command: "vllm serve microsoft/DialoGPT-medium",
expectErr: false,
},
{
name: "serve only command",
command: "serve --model microsoft/DialoGPT-medium",
command: "serve microsoft/DialoGPT-medium",
expectErr: false,
},
{
name: "args only",
command: "--model microsoft/DialoGPT-medium --tensor-parallel-size 2",
name: "positional model with flags",
command: "vllm serve microsoft/DialoGPT-medium --tensor-parallel-size 2",
expectErr: false,
},
{
name: "model with path",
command: "vllm serve /path/to/model --gpu-memory-utilization 0.8",
expectErr: false,
},
{
@@ -34,7 +39,7 @@ func TestParseVllmCommand(t *testing.T) {
},
{
name: "unterminated quote",
command: `vllm serve --model "unterminated`,
command: `vllm serve "unterminated`,
expectErr: true,
},
}
@@ -63,7 +68,7 @@ func TestParseVllmCommand(t *testing.T) {
}
func TestParseVllmCommandValues(t *testing.T) {
command := "vllm serve --model test-model --tensor-parallel-size 4 --gpu-memory-utilization 0.8 --enable-log-outputs"
command := "vllm serve test-model --tensor-parallel-size 4 --gpu-memory-utilization 0.8 --enable-log-outputs"
result, err := vllm.ParseVllmCommand(command)
if err != nil {