Zheng Han's picture

33 1 3

Zheng Han

traphix

·

AI & ML interests

None yet

Organizations

None yet

New activity in Qwen/Qwen3-Next-80B-A3B-Instruct-FP8 2 months ago

Error on 4 x L40s

#4 opened 2 months ago by

I got ValueError

#3 opened 2 months ago by

New activity in shanjiaz/qwen3-80b-fp8-dynamic 2 months ago

How to run this model via vllm？

#2 opened 3 months ago by

New activity in Qwen/Qwen3-Next-80B-A3B-Instruct 2 months ago

FP8 please

#18 opened 3 months ago by

New activity in DevQuasar/Qwen.Qwen3-Next-80B-A3B-Instruct-FP8-Dynamic 3 months ago

vllm v0.10.2 error

#2 opened 3 months ago by

New activity in DevQuasar/Qwen.Qwen3-Next-80B-A3B-Instruct-FP8 3 months ago

VLLM compatibility?

#1 opened 3 months ago by

New activity in shanjiaz/qwen3-80b-fp8-dynamic 3 months ago

Instruct or Thinking?

#1 opened 3 months ago by

New activity in DevQuasar/Qwen.Qwen3-Next-80B-A3B-Instruct-FP8-Dynamic 3 months ago

Could you share your quantization code？

#1 opened 3 months ago by

New activity in nm-testing/qwen3-80b-fp8-dynamic 3 months ago

Instruct or thinking？

#1 opened 3 months ago by

New activity in RedHatAI/Qwen3-8B-FP8-dynamic 3 months ago

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

#1 opened 3 months ago by

New activity in chriswritescode/Qwen3-235B-A22B-Instruct-2507-AWQ-Swift 4 months ago

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

#1 opened 4 months ago by

New activity in Qwen/Qwen2.5-14B-Instruct-1M 4 months ago

Does vllm 0.7.3 support this model？

#10 opened 9 months ago by

New activity in RedHatAI/README 4 months ago

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

#1 opened 4 months ago by

New activity in RedHatAI/DeepSeek-R1-0528-quantized.w4a16 6 months ago

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

#2 opened 6 months ago by

New activity in Qwen/Qwen3-30B-A3B-FP8 6 months ago

Remove vLLM FP8 Limitation

#2 opened 7 months ago by

New activity in RedHatAI/Qwen3-235B-A22B-FP8-dynamic 7 months ago

Error running on A100?

#4 opened 7 months ago by

Any plans for int8 quantized.w8a8?

#5 opened 7 months ago by

New activity in justinjja/Qwen3-235B-A22B-INT4-W4A16 7 months ago

How about int8 quantization?

#3 opened 7 months ago by

New activity in RedHatAI/Qwen3-235B-A22B-FP8-dynamic 7 months ago

How many RAM in GBs when quantizing Qwen3-235B-A22B?

#2 opened 7 months ago by

Where are the safetensors?

#1 opened 7 months ago by