[Voxtral TTS] Remove redundant yaml (#2056)

Signed-off-by: Chen-Yo Sun <chenyo.sun@mistral.ai>

vllm_omni/model_executor/stage_configs/voxtral_tts_1773881731.yaml

@@ -1,46 +0,0 @@
-async_chunk: true
-stage_args:
-- stage_id: 0
-  stage_type: llm
-  runtime: {process: true, devices: '0'}
-  engine_args: {max_num_seqs: 32, model_stage: audio_generation, model_arch: VoxtralTTSForConditionalGeneration,
-    worker_type: ar, worker_cls: vllm_omni.worker.gpu_ar_worker.GPUARWorker, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
-    gpu_memory_utilization: 0.8, enforce_eager: false, trust_remote_code: true, async_scheduling: true,
-    engine_output_type: latent, enable_prefix_caching: false, tokenizer_mode: mistral,
-    config_format: mistral, skip_mm_profiling: true, enable_chunked_prefill: false,
-    max_model_len: 4096, custom_process_next_stage_input_func: vllm_omni.model_executor.stage_input_processors.voxtral_tts.generator2tokenizer_async_chunk}
-  output_connectors: {to_stage_1: connector_of_shared_memory}
-  is_comprehension: true
-  final_output: false
-  final_output_type: text
-  default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 2048,
-    seed: 42, detokenize: true, repetition_penalty: 1.1}
-- stage_id: 1
-  stage_type: llm
-  runtime: {process: true, devices: '0'}
-  engine_args: {max_num_seqs: 32, model_stage: audio_tokenizer, model_arch: VoxtralTTSForConditionalGeneration,
-    worker_type: generation, worker_cls: vllm_omni.worker.gpu_generation_worker.GPUGenerationWorker,
-    scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler,
-    async_scheduling: false, gpu_memory_utilization: 0.1, enforce_eager: true, trust_remote_code: true,
-    enable_prefix_caching: false, skip_mm_profiling: true, engine_output_type: audio,
-    tokenizer_mode: mistral, config_format: mistral, max_num_batched_tokens: 65536,
-    max_model_len: 65536}
-  engine_input_source: [0]
-  is_comprehension: false
-  final_output: true
-  final_output_type: audio
-  input_connectors: {from_stage_0: connector_of_shared_memory}
-  tts_args: {max_instructions_length: 500}
-  default_sampling_params: {temperature: 0.9, top_p: 0.8, top_k: 40, max_tokens: 2048,
-    seed: 42, detokenize: true, repetition_penalty: 1.05}
-runtime:
-  enabled: true
-  defaults: {window_size: -1, max_inflight: 1}
-  connectors:
-    connector_of_shared_memory:
-      name: SharedMemoryConnector
-      extra: {shm_threshold_bytes: 65536, codec_streaming: true, connector_get_sleep_s: 0.01,
-        connector_get_max_wait_first_chunk: 3000, connector_get_max_wait: 300, codec_chunk_frames: 25,
-        codec_chunk_frames_at_begin: 5, codec_left_context_frames: 25}
-  edges:
-  - {from: 0, to: 1, window_size: -1}