VLLM 和 Sglang 部署 Qwen3-Omni,GPU 的利用率都不高,请问是什么原因? #114
#27 opened 4 days ago
		by
		
				
							
						yixue
	
When will the vLLM implementation with the Talker module be available?
								1
#26 opened 7 days ago
		by
		
				
							
						mifanbushipeicai
	
GPTQ 4-bit quant
#25 opened 9 days ago
		by
		
				
							
						thomasip
	
Configuration needed
#24 opened 14 days ago
		by
		
				
							
						vladciocan88
	
iPad Pro M5 with 16GM RAM
#23 opened 19 days ago
		by
		
				
							
						Arete7
	
Where's the FP8 quant?
👍
							
						2
				
								1
#22 opened about 1 month ago
		by
		
				
							
						marksverdhei
	
Qwen3-Omni ASR with Transformers only transcribes first 30s of long audio
🤝
							👀
							
						4
				
								3
#21 opened about 1 month ago
		by
		
				
							
						AndreosLXIX
	
USE_AUDIO_IN_VIDEO Error
								1
#20 opened about 1 month ago
		by
		
				
							
						jiyeoncoco
	
Request: DOI
#19 opened about 1 month ago
		by
		
				
							
						amrkfahmy
	
fine tuning
#18 opened about 1 month ago
		by
		
				
							
						rorosese
	
🚀 Best Practices for Evaluating the Qwen3-Omni Model
#16 opened about 1 month ago
		by
		
				
							
						Yunxz
	
Will the Qwen3-Omni-Flash-Instruct and Qwen3-Omni-Flash-Thinking models be open-sourced?
								3
#15 opened about 1 month ago
		by
		
				
							
						Jackie219
	
Possible to run with 24GB VRAM?
								4
#14 opened about 1 month ago
		by
		
				
							
						happyTonakai
	
Requesting for a guide to train model on new languages if possible
🔥
							
						1
				
								1
#13 opened about 1 month ago
		by
		
				
							
						dumbass10
	
Model halucinates when running paralel requests in vllm
#12 opened about 1 month ago
		by
		
				
							
						vladciocan88
	
Requesting README.md update on how to run the model on vLLM with tool-calling support
🤝
							🔥
							
						10
				#11 opened about 1 month ago
		by
		
				
							
						douglasrfaisal-gl
	
Would you release the pre-trained AuT model?
👍
							
						10
				
								1
#10 opened about 1 month ago
		by
		
				
							
						JosephusCheung
	
Update README.md
								1
#9 opened about 1 month ago
		by
		
				
							
						CHNtentes
	
🚀 Qwen3-Omni Fine-tuning support. (transformers & Megatron)
								2
#8 opened about 1 month ago
		by
		
				
							
						study-hjt
	
Unable to import Qwen3OmniMoeForConditionalGeneration and Qwen3OmniMoeProcessor
👍
							
						3
				
								3
#6 opened about 1 month ago
		by
		
				
							
						Shashank14
	
Apple Silicon support ?
👍
							👀
							
						4
				
								2
#5 opened about 1 month ago
		by
		
				
							
						Novell
	
Support for mixed modality
								1
#4 opened about 1 month ago
		by
		
				
							
						YujiaX
	
Local Installation Video and Testing - Step by Step
👍
							
						1
				#3 opened about 1 month ago
		by
		
				
							
						fahdmirzac
	
Example of how to set up Qwen3-omni for audio-input audio-output
👍
							🔥
							
						9
				
								2
#2 opened about 1 month ago
		by
		
				
							
						abidlabs
	
AWQs Please!!!
👍
							➕
							
						25
				
								1
#1 opened about 1 month ago
		by
		
				
							
						VivekMalipatel23