Add MLX command parsing and routing support

This commit is contained in:
2025-09-16 21:39:08 +02:00
parent 63fea02d66
commit 154b754aff
3 changed files with 67 additions and 1 deletions

View File

@@ -62,7 +62,7 @@ func (im *instanceManager) CreateInstance(name string, options *instance.CreateI
im.onStatusChange(name, oldStatus, newStatus) im.onStatusChange(name, oldStatus, newStatus)
} }
inst := instance.NewInstance(name, &im.instancesConfig, options, statusCallback) inst := instance.NewInstance(name, &im.backendsConfig, &im.instancesConfig, options, statusCallback)
im.instances[inst.Name] = inst im.instances[inst.Name] = inst
if err := im.persistInstance(inst); err != nil { if err := im.persistInstance(inst); err != nil {
@@ -260,6 +260,10 @@ func (im *instanceManager) getPortFromOptions(options *instance.CreateInstanceOp
if options.LlamaServerOptions != nil { if options.LlamaServerOptions != nil {
return options.LlamaServerOptions.Port return options.LlamaServerOptions.Port
} }
case backends.BackendTypeMlxLm:
if options.MlxServerOptions != nil {
return options.MlxServerOptions.Port
}
} }
return 0 return 0
} }
@@ -271,6 +275,10 @@ func (im *instanceManager) setPortInOptions(options *instance.CreateInstanceOpti
if options.LlamaServerOptions != nil { if options.LlamaServerOptions != nil {
options.LlamaServerOptions.Port = port options.LlamaServerOptions.Port = port
} }
case backends.BackendTypeMlxLm:
if options.MlxServerOptions != nil {
options.MlxServerOptions.Port = port
}
} }
} }

View File

@@ -7,6 +7,7 @@ import (
"io" "io"
"llamactl/pkg/backends" "llamactl/pkg/backends"
"llamactl/pkg/backends/llamacpp" "llamactl/pkg/backends/llamacpp"
"llamactl/pkg/backends/mlx"
"llamactl/pkg/config" "llamactl/pkg/config"
"llamactl/pkg/instance" "llamactl/pkg/instance"
"llamactl/pkg/manager" "llamactl/pkg/manager"
@@ -684,3 +685,57 @@ func (h *Handler) ParseLlamaCommand() http.HandlerFunc {
} }
} }
} }
// ParseMlxCommand godoc
// @Summary Parse mlx_lm.server command
// @Description Parses MLX-LM server command string into instance options
// @Tags backends
// @Security ApiKeyAuth
// @Accept json
// @Produce json
// @Param request body ParseCommandRequest true "Command to parse"
// @Success 200 {object} instance.CreateInstanceOptions "Parsed options"
// @Failure 400 {object} map[string]string "Invalid request or command"
// @Router /backends/mlx/parse-command [post]
func (h *Handler) ParseMlxCommand() http.HandlerFunc {
type errorResponse struct {
Error string `json:"error"`
Details string `json:"details,omitempty"`
}
writeError := func(w http.ResponseWriter, status int, code, details string) {
w.Header().Set("Content-Type", "application/json")
w.WriteHeader(status)
_ = json.NewEncoder(w).Encode(errorResponse{Error: code, Details: details})
}
return func(w http.ResponseWriter, r *http.Request) {
var req ParseCommandRequest
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
writeError(w, http.StatusBadRequest, "invalid_request", "Invalid JSON body")
return
}
if strings.TrimSpace(req.Command) == "" {
writeError(w, http.StatusBadRequest, "invalid_command", "Command cannot be empty")
return
}
mlxOptions, err := mlx.ParseMlxCommand(req.Command)
if err != nil {
writeError(w, http.StatusBadRequest, "parse_error", err.Error())
return
}
// Currently only support mlx_lm backend type
backendType := backends.BackendTypeMlxLm
options := &instance.CreateInstanceOptions{
BackendType: backendType,
MlxServerOptions: mlxOptions,
}
w.Header().Set("Content-Type", "application/json")
if err := json.NewEncoder(w).Encode(options); err != nil {
writeError(w, http.StatusInternalServerError, "encode_error", err.Error())
}
}
}

View File

@@ -55,6 +55,9 @@ func SetupRouter(handler *Handler) *chi.Mux {
r.Route("/llama-cpp", func(r chi.Router) { r.Route("/llama-cpp", func(r chi.Router) {
r.Post("/parse-command", handler.ParseLlamaCommand()) r.Post("/parse-command", handler.ParseLlamaCommand())
}) })
r.Route("/mlx", func(r chi.Router) {
r.Post("/parse-command", handler.ParseMlxCommand())
})
}) })
// Instance management endpoints // Instance management endpoints