Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
Orchestrating LLM KV-Cache across GPU–DRAM–SSD with Attention-Aware Hotness Scheduling
Published in Targeting SC 2026, 2026
Manuscript and artifact in progress. Project artifact: OrchKvCache.
Recommended citation: Ziqing Li, "Orchestrating LLM KV-Cache across GPU–DRAM–SSD with Attention-Aware Hotness Scheduling." Targeting SC 2026.
Algebraically Identity-Preserving KV Tiering for Memory-Bounded Long-Context Inference
Published in Targeting EMNLP 2026 (ARR), 2026
Manuscript and artifact in progress. Project artifact: HALO.
Recommended citation: Ziqing Li, "Algebraically Identity-Preserving KV Tiering for Memory-Bounded Long-Context Inference." Targeting EMNLP 2026 (ARR).
Schedulable KV-Cache Eviction with a Probabilistic Sizing Bound for Real-Time LLM Decoding
Published in Targeting IEEE RTSS 2026, 2026
Manuscript and artifact in progress. Project artifact: SEER.
Recommended citation: Ziqing Li, "Schedulable KV-Cache Eviction with a Probabilistic Sizing Bound for Real-Time LLM Decoding." Targeting IEEE RTSS 2026.
Mining Attention Dynamics: Auditing KV-Saliency Prediction in LLMs
Published in Targeting IEEE ICDM 2026, 2026
Manuscript and artifact in progress. Project artifact: XQP / KVSalienceBench.
Recommended citation: Ziqing Li, "Mining Attention Dynamics: Auditing KV-Saliency Prediction in LLMs." Targeting IEEE ICDM 2026.
Direction Is Not a Knob: Cross-GPU KV-Cache Handoff Contention on NVLink
Published in Targeting IEEE ICCD 2026, 2026
Manuscript and artifact in progress. Project artifact: PeerKV.
Recommended citation: Ziqing Li, "Direction Is Not a Knob: Cross-GPU KV-Cache Handoff Contention on NVLink." Targeting IEEE ICCD 2026.
OrchKvCache: Orchestrating LLM KV-Cache across GPU-DRAM-SSD with Attention-Aware Hotness Scheduling
Published in Targeting SC 2026, 2026
HALO: Algebraically Identity-Preserving KV Tiering for Memory-Bounded Long-Context Inference
Published in Targeting EMNLP 2026 (ARR), 2026
SEER: Schedulable KV-Cache Eviction with a Probabilistic Sizing Bound for Real-Time LLM Decoding
Published in Targeting IEEE RTSS 2026, 2026
Mining Attention Dynamics: Auditing KV-Saliency Prediction in LLMs
Published in Targeting IEEE ICDM 2026, 2026
Direction Is Not a Knob: Cross-GPU KV-Cache Handoff Contention on NVLink
Published in Targeting IEEE ICCD 2026, 2026
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.