EDBT 2026 Demo / reviewers in the wild / expert
Ramya Prabhu
dblp:356/4824
· DBLP profile ↗
2ranked-venue papers
1as first author
2since 2021 · last 2025
0009-0002-7266-5522ORCID · corroborated
Domains — the database's venue-derived domains; a paper can count in several
Systems, architecture and hardware · 2 · 1 first-author · 2 since 2021Software engineering, systems software and programming languages · 2 · 1 first-author · 2 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Computer architecture, parallel and distributed computing, and storage systems
1 paper |
Memory systems · 67% GPUs and heterogeneous computing · 33% | |
| Artificial intelligence
2 papers |
Language models and text generation · 56% Efficient and distributed learning · 44% | |
| Databases, data mining, and information retrieval
1 paper |
Machine learning and data management · 100% |
Topics — the 6 heaviest of 7, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Natural language and speech › Language models and text generation
large language model inference |
0.9 | 1 | 2025 | POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference · ASPLOS (2) 2025 |
Machine learning › Efficient and distributed learning › inference serving
large language model serving |
0.9 | 1 | 2025 | vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention · ASPLOS (1) 2025 |
Memory systems › memory management › memory allocation
dynamic memory allocation |
0.9 | 1 | 2025 | vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention · ASPLOS (1) 2025 |
GPUs and heterogeneous computing
GPU memory management |
0.9 | 1 | 2025 | vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention · ASPLOS (1) 2025 |
Memory systems › cache management
KV cache management |
0.9 | 1 | 2025 | vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention · ASPLOS (1) 2025 |
Natural language and speech › Language models and text generation
large language model |
0.3 | 1 | 2025 | POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference · ASPLOS (2) 2025 |
Methods — techniques the papers use, named apart from their topics
virtual memory management · 2.6attention · 0.9
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2025 | POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
Aditya K. Kamath, Ramya Prabhu, Jayashree Mohan, Simon Peter 0001, Ramachandran Ramjee, Ashish Panwar |
ASPLOS (2) | 2 |
| 2025 | vAttention: Dynamic Memory Management for Serving LLMs without PagedAttentionabstractPagedAttention is a popular approach for dynamic memory allocation in LLM serving systems. It enables on-demand allocation of GPU memory to mitigate KV cache fragmentation - a phenomenon that crippled the batch size (and consequently throughput) in prior systems. However, in trying to allocate physical memory at runtime, PagedAttention ends up changing the virtual memory layout of the KV cache from contiguous to non-contiguous. Such a design leads to non-trivial programming and performance overheads. Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar |
ASPLOS (1) | 1 |