[perf] Minicpm o4.5 optimization (#5228)

Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Co-authored-by: Sy03 <1370724210@qq.com>

vllm_omni/deploy/minicpmo_4_5_8x4090.yaml

@@ -4,10 +4,8 @@
 #                                  thinker weights take ~17.5 GB per card
 #                                  on 4090, leaving ~3 GB for KV cache /
 #                                  activations).
-# Stage 1 (talker) : GPU 4       — MiniCPMTTS + Token2Wav, ~90% mem
-#                                  (covers both the talker LM and the
-#                                  in-process Token2Wav vocoder that emits
-#                                  the waveform).
+# Stage 1 (talker) : GPU 4       — MiniCPMTTS codec generation, ~90% mem.
+# Stage 2 (code2wav): GPU 5      — codec-to-waveform generation, ~90% mem.
 #
 # max_model_len is pinned to 4096 because the upstream config.json
 # advertises max_position_embeddings=40960 (tuned for H20 141GB); on a
@@ -16,11 +14,21 @@
 # this thinker model + vision/audio encoders + Whisper preallocation,
 # so 4096 is the empirically-verified safe ceiling.
 pipeline: minicpmo_4_5
-async_chunk: false
+async_chunk: true
 
 trust_remote_code: true
 enable_prefix_caching: false
 
+connectors:
+  connector_of_shared_memory:
+    name: SharedMemoryConnector
+    extra:
+      connector_get_sleep_s: 0.01
+      connector_get_max_wait_first_chunk: 3000
+      connector_get_max_wait: 300
+      codec_chunk_frames: 25
+      codec_left_context_frames: 3
+
 stages:
   - stage_id: 0
     max_num_seqs: 1
@@ -42,19 +50,40 @@ stages:
       repetition_penalty: 1.1
 
   - stage_id: 1
-    # Talker only consumes runtime_additional_information[0]; any value > 1
-    # makes concurrent requests share request-0's audio (mm_outputs fallback).
     max_num_seqs: 1
     gpu_memory_utilization: 0.9
     enforce_eager: true
     max_num_batched_tokens: 8192
     devices: "4"
+    output_connectors:
+      to_stage_2: connector_of_shared_memory
+    # vLLM samples the binary continue/stop row; codec sampling comes from
+    # the checkpoint's tts_config and currently uses a deterministic seed.
     default_sampling_params:
       temperature: 0.0
       top_p: 1.0
       top_k: -1
-      max_tokens: 1
+      min_tokens: 50
+      max_tokens: 2048
+      stop_token_ids: [1]
       seed: 42
       detokenize: false
 
+  - stage_id: 2
+    max_num_seqs: 1
+    gpu_memory_utilization: 0.9
+    enforce_eager: true
+    enable_chunked_prefill: false
+    max_num_batched_tokens: 65536
+    max_model_len: 65536
+    devices: "5"
+    input_connectors:
+      from_stage_1: connector_of_shared_memory
+    default_sampling_params:
+      temperature: 0.0
+      top_p: 1.0
+      top_k: -1
+      max_tokens: 65536
+      detokenize: true
+
 platforms: {}