wenhua cheng's picture

wenhua cheng

wenhuach

·

wenhuach21

AI & ML interests

Model Compression, CV

Recent Activity

new activity 1 day ago

Intel/Qwen3.5-35B-A3B-int4-AutoRound:Thanks! And MTP key question

new activity 1 day ago

Intel/GLM-5-int4-mixed-AutoRound:vLLM fails to serve Intel/GLM-5-int4-mixed-AutoRound on NVIDIA DGX Spark (GB10, sm121) due to no valid MLA attention backend (qk_nope_head_dim 192)

liked a model 2 days ago

kaitchup/Qwen3.5-27B-autoround-W4A16

View all activity

Organizations

Posts 15

Post

2976

🚀 SignRoundV2 for LLM quantization: PTQ-level cost, QAT-level accuracy — yes, even at 2 bits.

SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs (2512.04746)

Articles 1

Article

44

Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMs

View all Articles

Papers 3

arxiv:2512.04746

arxiv:2310.10944

arxiv:2309.05516

models 0

None public yet

datasets 0

None public yet