Skip to content

fix triton token2wav model cache thread unsafety #1622

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
+5 −3
Open

fix triton token2wav model cache thread unsafety #1622

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cd26dd1
fix triton token2wav model cache thread unsafety
GoyoUijin Oct 27, 2025
fa27814
Revert "fix triton token2wav model cache thread unsafety"
GoyoUijin Oct 27, 2025
e8bf717
Fix: generate token2wav_request_id from cosyvoice2
GoyoUijin Oct 27, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions runtime/triton_trtllm/model_repo/cosyvoice2/1/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@
import os
import threading
import time
from uuid import uuid4

import numpy as np
import torch
Expand Down Expand Up @@ -364,6 +365,7 @@ def execute(self, requests):
# Generate semantic tokens with LLM
generated_ids_iter = self.forward_llm(input_ids)

token2wav_request_id = request_id or str(uuid4())
if self.decoupled:
response_sender = request.get_response_sender()

Expand Down Expand Up @@ -392,7 +394,7 @@ def execute(self, requests):
this_tts_speech_token = torch.tensor(this_tts_speech_token).unsqueeze(dim=0).to(torch.int32).to(self.device)

sub_tts_speech = self.forward_token2wav(
this_tts_speech_token, request_id, prompt_speech_tokens,
this_tts_speech_token, token2wav_request_id, prompt_speech_tokens,
prompt_speech_feat, prompt_spk_embedding, token_offset, False
)

Expand Down Expand Up @@ -427,7 +429,7 @@ def execute(self, requests):
time.sleep(0.02)

this_tts_speech_token = torch.tensor(semantic_token_ids_arr).unsqueeze(dim=0).to(torch.int32).to(self.device)
sub_tts_speech = self.forward_token2wav(this_tts_speech_token, request_id, prompt_speech_tokens, prompt_speech_feat, prompt_spk_embedding, token_offset, True)
sub_tts_speech = self.forward_token2wav(this_tts_speech_token, token2wav_request_id, prompt_speech_tokens, prompt_speech_feat, prompt_spk_embedding, token_offset, True)
audio_tensor = pb_utils.Tensor.from_dlpack("waveform", to_dlpack(sub_tts_speech))
inference_response = pb_utils.InferenceResponse(output_tensors=[audio_tensor])
response_sender.send(inference_response)
Expand All @@ -441,7 +443,7 @@ def execute(self, requests):
if generated_ids is None or len(generated_ids) == 0:
raise pb_utils.TritonModelException("Generated IDs is None or empty")

audio = self.forward_token2wav(generated_ids, request_id, prompt_speech_tokens, prompt_speech_feat, prompt_spk_embedding)
audio = self.forward_token2wav(generated_ids, token2wav_request_id, prompt_speech_tokens, prompt_speech_feat, prompt_spk_embedding)

# Prepare response
audio_tensor = pb_utils.Tensor.from_dlpack("waveform", to_dlpack(audio))
Expand Down