Pengle Zhang
4 papers · 2023–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
Venues
Top co-authors
Research topics
Keywords
model compression
(1)
transformer architecture
(1)
attention mechanism
(1)
parameter-efficient learning
(1)
computational efficiency
(1)
parameter efficient
(1)
language model
(1)
inference efficiency
(1)
parameter efficiency
(1)
inference acceleration
(1)
sequence compression
(1)
matrix multiplication
(1)
context memory
(1)
attention computation
(1)
large language model
(1)
neural network
(1)
plug-and-play module
(1)
int4 quantization
(1)
8-bit quantization
(1)
fp8 quantization
(1)
Papers
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
ICML 2025
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
ICLR 2025
InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
NeurIPS 2024
Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules
EMNLP 2023