Zheng Han

traphix's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model about 1 month ago

RedHatAI/Qwen3-Next-80B-A3B-Instruct-quantized.w4a16

Text Generation • 12B • Updated 3 days ago • 504 • 3

New activity in RedHatAI/Qwen3-Next-80B-A3B-Instruct-quantized.w4a16 about 1 month ago

Tokenizer you are loading with an incorrect regex pattern

1

#2 opened 3 months ago by

traphix

New activity in Intel/Qwen3-Next-80B-A3B-Instruct-int4-AutoRound 3 months ago

Failed to find a kernel that can implement the WNA16 linear layer

#1 opened 3 months ago by

traphix

New activity in RedHatAI/Qwen3-Next-80B-A3B-Instruct-quantized.w4a16 3 months ago

vllm error: Extra inputs are not permitted

#1 opened 3 months ago by

traphix

New activity in RedHatAI/Qwen3-235B-A22B-Instruct-2507-NVFP4 3 months ago

Can A100 run Qwen3-235B-A22B-Instruct-2507-NVFP4?

#1 opened 3 months ago by

traphix

New activity in Qwen/Qwen3-Next-80B-A3B-Instruct-FP8 5 months ago

Error on 4 x L40s

➕ 2

1

#4 opened 5 months ago by

traphix

I got ValueError

👀 2

10

#3 opened 5 months ago by

spow12

New activity in shanjiaz/qwen3-80b-fp8-dynamic 5 months ago

How to run this model via vllm？

11

#2 opened 5 months ago by

traphix

New activity in Qwen/Qwen3-Next-80B-A3B-Instruct 5 months ago

FP8 please

👀 ➕ 16

8

#18 opened 6 months ago by

aliquis-pe

New activity in DevQuasar/Qwen.Qwen3-Next-80B-A3B-Instruct-FP8-Dynamic 5 months ago

vllm v0.10.2 error

❤️ 1

#2 opened 5 months ago by

traphix

New activity in DevQuasar/Qwen.Qwen3-Next-80B-A3B-Instruct-FP8 5 months ago

VLLM compatibility?

9

#1 opened 6 months ago by

aidendle94

New activity in shanjiaz/qwen3-80b-fp8-dynamic 5 months ago

Instruct or Thinking?

#1 opened 5 months ago by

traphix

New activity in DevQuasar/Qwen.Qwen3-Next-80B-A3B-Instruct-FP8-Dynamic 6 months ago

Could you share your quantization code？

1

#1 opened 6 months ago by

traphix

New activity in nm-testing/qwen3-80b-fp8-dynamic 6 months ago

Instruct or thinking？

#1 opened 6 months ago by

traphix

New activity in RedHatAI/Qwen3-8B-FP8-dynamic 6 months ago

Any plans to quantize Qwen3-235B-A22B-Instruct-2507？

#1 opened 6 months ago by

traphix

New activity in chriswritescode/Qwen3-235B-A22B-Instruct-2507-AWQ-Swift 7 months ago

Qwen3-235B-A22B-Instruct-2507, int4-w4a16 or awq? Which one has better accuracy recovery?

1

#1 opened 7 months ago by

traphix

New activity in Qwen/Qwen2.5-14B-Instruct-1M 7 months ago

Does vllm 0.7.3 support this model？

1

#10 opened 12 months ago by

traphix

New activity in RedHatAI/README 7 months ago

Any plans to quantize Qwen3-235B-A22B-Instruct-2507？

#1 opened 7 months ago by

traphix

New activity in RedHatAI/DeepSeek-R1-0528-quantized.w4a16 9 months ago

Is 4 x H20 96G sufficient to run this model?

2

#2 opened 9 months ago by

milongwong

New activity in Qwen/Qwen3-30B-A3B-FP8 9 months ago

Remove vLLM FP8 Limitation

10

#2 opened 10 months ago by

simon-mo