Ilker ManapandClaude Opus 5.5
4f280a3546
A node that cannot run the CUDA 13 build installs the same version's CUDA 12.9 build from vLLM's GitHub release, with PyTorch's cu129 torch; the install computes on the GPU before it counts. The build can be chosen per node — auto, cu13, cu129, none — on the cluster page, with ctl engine-build, or over the admin API; the control plane keeps the choice and tells the node at once. Refs #2. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
39 lines
1.5 KiB
Go
39 lines
1.5 KiB
Go
package cli
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
|
|
"github.com/spf13/cobra"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/control/adminapi"
|
|
)
|
|
|
|
func newEngineBuildCmd(client func() *ctlClient) *cobra.Command {
|
|
return &cobra.Command{
|
|
Use: "engine-build <node> <engine> <build>",
|
|
Short: "Choose which build of an engine a GPU node installs",
|
|
Long: "A node installs the build of vLLM its hardware runs: CUDA 13 where the\n" +
|
|
"driver and GPUs allow, else the same version built for CUDA 12.9. This\n" +
|
|
"chooses instead, as the cluster page's vLLM build column does:\n\n" +
|
|
" auto what the hardware runs (the default)\n" +
|
|
" cu13 the CUDA 13 build, from PyPI\n" +
|
|
" cu129 the CUDA 12.9 build, from vLLM's GitHub release\n" +
|
|
" none no vLLM on this node\n\n" +
|
|
"The node is told at once and installs it in the background; a build it\n" +
|
|
"cannot compute with on its GPU fails to install, saying why, and the\n" +
|
|
"cluster page shows it.\n\n" +
|
|
" llmgw ctl engine-build gpu07 vllm cu129",
|
|
Args: cobra.ExactArgs(3),
|
|
RunE: func(cmd *cobra.Command, args []string) error {
|
|
body, _ := json.Marshal(adminapi.NodeEngineRequest{Engine: args[1], Build: args[2]})
|
|
if err := client().post(cmd.Context(), "/api/v1/nodes/"+args[0]+"/engines", body, nil); err != nil {
|
|
return err
|
|
}
|
|
fmt.Fprintf(cmd.OutOrStdout(), "%s: %s build %s; the node installs it in the background (llmgw ctl nodes shows it)\n",
|
|
args[0], args[1], args[2])
|
|
return nil
|
|
},
|
|
}
|
|
}
|