Zheng Han's picture

10 1 1

Zheng Han

traphix

·

AI & ML interests

None yet

Recent Activity

new activity 4 days ago

cognitivecomputations/DeepSeek-V3-AWQ:Is there any accuracy results comparing to original DeepSeek-V3？

new activity 4 days ago

cognitivecomputations/DeepSeek-R1-AWQ:why "MLA is not supported with awq_marlin quantization. Disabling MLA." with 4090 * 32 (4 node / vllm 0.7.2)

new activity 4 days ago

cognitivecomputations/DeepSeek-R1-AWQ:Is there any accuracy results comparing to original DeepSeek-R1？

View all activity

Organizations

None yet

traphix's activity

New activity in cognitivecomputations/DeepSeek-V3-AWQ 4 days ago

Is there any accuracy results comparing to original DeepSeek-V3？

#6 opened 4 days ago by

New activity in cognitivecomputations/DeepSeek-R1-AWQ 4 days ago

why "MLA is not supported with awq_marlin quantization. Disabling MLA." with 4090 * 32 (4 node / vllm 0.7.2)

#14 opened 4 days ago by

Is there any accuracy results comparing to original DeepSeek-R1？

#15 opened 4 days ago by

New activity in cognitivecomputations/DeepSeek-R1-AWQ 8 days ago

Has anyone evaluated the performance of the AWQ version of the model on benchmarks?

#8 opened 12 days ago by

New activity in cognitivecomputations/DeepSeek-R1-AWQ 13 days ago

skips the thinking process

#5 opened 16 days ago by

Deployment framework

#2 opened about 1 month ago by

New activity in cognitivecomputations/DeepSeek-V3-AWQ 13 days ago

vllm support a100

#2 opened about 1 month ago by

HuggingLianWang

New activity in neuralmagic/Qwen2.5-72B-quantized.w8a8 15 days ago

Any plans to quantize Qwen/Qwen2.5-72B-Instruct to w8a8？

#1 opened 15 days ago by

New activity in neuralmagic/DeepSeek-Coder-V2-Instruct-FP8 6 months ago

Can it run on A100/A800 with VLLM?

#1 opened 7 months ago by

Parkerlambert123

Quantize DeepSeek-Coder-V2-Instruct to W8A8(INT8)?

#2 opened 6 months ago by