Struct MockEngineArgs 

pub struct MockEngineArgs {

    pub num_gpu_blocks: usize,
    pub block_size: usize,
    pub max_num_seqs: Option<usize>,
    pub max_num_batched_tokens: Option<usize>,
    pub enable_prefix_caching: bool,
    pub enable_chunked_prefill: bool,
    pub watermark: f64,
    pub speedup_ratio: f64,
    pub dp_size: u32,
    pub startup_time: Option<f64>,
    pub worker_type: WorkerType,
    pub perf_model: Arc<PerfModel>,
    pub enable_local_indexer: bool,
    pub bootstrap_port: Option<u16>,
    pub kv_bytes_per_token: Option<usize>,
    pub kv_transfer_bandwidth: Option<f64>,
    pub reasoning: Option<ReasoningConfig>,
    pub zmq_kv_events_port: Option<u16>,
}

Configuration arguments for MockVllmEngine

Fields

num_gpu_blocks: usize

block_size: usize

max_num_seqs: Option<usize>

max_num_batched_tokens: Option<usize>

enable_prefix_caching: bool

enable_chunked_prefill: bool

watermark: f64

speedup_ratio: f64

dp_size: u32

startup_time: Option<f64>

Optional startup time in seconds to simulate engine initialization delay

worker_type: WorkerType

Worker type for disaggregated serving (Aggregated, Prefill, or Decode)

perf_model: Arc<PerfModel>

Performance model for timing predictions (not serialized, loaded from planner_profile_data)

enable_local_indexer: bool

Enable worker-local KV indexer for tracking this worker’s own KV cache state

bootstrap_port: Option<u16>

Bootstrap port for disaggregated serving rendezvous. Prefill workers listen on this port; decode workers connect to it. If None, bootstrap rendezvous is disabled.

kv_bytes_per_token: Option<usize>

KV cache bytes per token, auto-computed from model config by Python CLI. Formula: num_layers * 2 * num_kv_heads * head_dim * dtype_bytes

kv_transfer_bandwidth: Option<f64>

KV cache transfer bandwidth in GB/s for disaggregated serving latency simulation. Default: 64.0 (inter-node InfiniBand). Set to 0 to disable KV transfer delay. For intra-node NVLink, typical value is ~450.

reasoning: Option<ReasoningConfig>

Reasoning/thinking token configuration. When set, the mocker wraps output in thinking boundary tokens.

zmq_kv_events_port: Option<u16>

ZMQ port for publishing KV events in vLLM’s native wire format. When set, the scheduler publishes to a ZMQ PUB socket instead of directly to NATS. A KvEventPublisher relay subscribes to this socket and forwards events to NATS.

Implementations

impl MockEngineArgs

pub fn builder() -> MockEngineArgsBuilder

pub fn is_prefill(&self) -> bool

pub fn is_decode(&self) -> bool

pub fn needs_kv_publisher(&self) -> bool

pub fn from_json_file(path: &Path) -> Result<Self>

Create MockEngineArgs from a JSON file containing extra engine arguments

Trait Implementations

impl Clone for MockEngineArgs

fn clone(&self) -> MockEngineArgs

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for MockEngineArgs

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for MockEngineArgs

fn default() -> MockEngineArgs

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for MockEngineArgs

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for MockEngineArgs

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Validate for MockEngineArgs

fn validate(&self) -> Result<(), ValidationErrors>

impl<'v_a> ValidateArgs<'v_a> for MockEngineArgs

type Args = ()

fn validate_with_args(&self, args: Self::Args) -> Result<(), ValidationErrors>