JC
Jianyi Cheng
cs.ARcs.LGcs.PLcs.CLcs.AIcs.PF
On Valency
published · living versionsW_vfnqaepu·v1 · currentpublished
BitDecoding-FP4: Native FP4 KV Cache Decoding via Algorithm-System Co-Design
with Dayou Du, Woon Yee Ng, Guangming Sheng, Nick Lau +1
1 version
Preprints & journals
16 papers in the corpus · 2021–2026E-Graphs as a Persistent Compiler Abstraction2602.16707v2 · Jules Merckx, Alexandre Lopoukhine, Samuel Coward et al.2026 · 0 citationsarXiv
Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference2509.09505v3 · Haoran Wu, Can Xiao, Jiayi Nie et al.2025 · 0 citationsarXiv
Refining Datapath for Microscaling ViTs2505.22194v2 · Can Xiao, Jianyi Cheng, Aaron Zhao2025 · 0 citationsarXiv
eqsat: An Equality Saturation Dialect for Non-destructive Rewriting2505.09363v2 · Jules Merckx, Alexandre Lopoukhine, Samuel Coward et al.2025 · 0 citationsarXiv
BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache2503.18773v3 · Dayou Du, Shijie Cao, Jianyi Cheng et al.2025 · 0 citationsarXiv
Scaling Laws For Mixed Quantization2410.06722v3 · Zeyu Cao, Boyang Gu, Cheng Zhang et al.2024 · 0 citationsarXiv
HASS: Hardware-Aware Sparsity Search for Dataflow DNN Accelerator2406.03088v1 · Zhewen Yu, Sudarshan Sreeram, Krish Agrawal et al.2024 · 2 citationsarXiv
LQER: Low-Rank Quantization Error Reconstruction for LLMs2402.02446v3 · Cheng Zhang, Jianyi Cheng, George A. Constantinides et al.2024 · 2 citationsarXiv
Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?2310.05079v2 · Cheng Zhang, Jianyi Cheng, Ilia Shumailov et al.2023 · 8 citationsarXiv
LLM4DV: Using Large Language Models for Hardware Test Stimuli Generation2310.04535v2 · Zixi Zhang, Balint Szekely, Pedro Gimenes et al.2023 · 28 citationsarXiv
GSA to HDL: Towards principled generation of dynamically scheduled circuits2308.11048v1 · Aditya Rajagopal, Diederik Adriaan Vink, Jianyi Cheng et al.2023 · 0 citationsarXiv
SEER: Super-Optimization Explorer for HLS using E-graph Rewriting with MLIR2308.07654v1 · Jianyi Cheng, Samuel Coward, Lorenzo Chelini et al.2023 · 1 citationarXiv
A Dataflow Compiler for Efficient LLM Inference using Custom Microscaling Formats2307.15517v2 · Jianyi Cheng, Cheng Zhang, Zhewen Yu et al.2023 · 1 citationarXiv
PASS: Exploiting Post-Activation Sparsity in Streaming Architectures for CNN Acceleration2307.07821v1 · Alexander Montgomerie-Corcoran, Zhewen Yu, Jianyi Cheng et al.2023 · 4 citationsarXiv
ScaleHLS: A New Scalable High-Level Synthesis Framework on Multi-Level Intermediate Representation2107.11673v4 · Hanchen Ye, Cong Hao, Jianyi Cheng et al.2021 · 79 citationsarXiv
Phism: Polyhedral High-Level Synthesis in MLIR2103.15103v1 · Ruizhe Zhao, Jianyi Cheng2021 · 3 citationsarXiv
Career total: 42 works. 16 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.