REVIEW 4 cited by
InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
The widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference escalate the memory requirement of the key-value (KV) cache, which imposes a huge burden on the GPU VRAM, especially for resource-constraint scenarios (e.g., edge computing and personal devices). Several cost-effective solutions leverage host memory or SSDs to reduce storage costs for offline inference scenarios and improve the throughput. Nevertheless, they suffer from significant performance penalties imposed by intensive KV cache accesses due to limited PCIe bandwidth. To address these issues, we propose InstInfer, a novel LLM inference system that offloads the most performance-critical computation (i.e., attention in decoding phase) and data (i.e., KV cache) parts to Computational Storage Drives (CSDs), which minimize the enormous KV transfer overheads. InstInfer designs a dedicated flash-aware in-storage attention engine with KV cache management mechanisms to exploit the high internal bandwidths of CSDs instead of being limited by the PCIe bandwidth. The optimized P2P transmission between GPU and CSDs further reduces data migration overheads. Experimental results demonstrate that for a 13B model using an NVIDIA A6000 GPU, InstInfer improves throughput for long-sequence inference by up to 11.1$\times$, compared to existing SSD-based solutions such as FlexGen.
Forward citations
Cited by 4 Pith papers
-
NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement
A heterogeneous GPU-PNM serving system that routes short prompts to GPUs and long prompts to near-memory sparse-attention devices, with runtime migration for growing contexts, reports large throughput and tail-latency...
-
HGCA: Hybrid GPU-CPU Attention for Long Context LLM Inference
HGCA splits attention between GPU (dense, recent KV) and CPU (sparse, salient KV) and merges partial results with exact log-sum-exp fusion, scaling long-context decoding on commodity GPUs.
-
Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU
LeoAM reports a 3.46x average latency speedup for long-context LLM inference on one commodity GPU by adaptively chunking KV data and loading compact key abstracts from disk instead of full KV values.
-
Recursive Offloading for LLM Serving in Multi-tier Networks
RecServe routes LLM requests across device, edge, and cloud using adaptive confidence thresholds based on recent history, cutting communication by over 50% versus cloud-only serving while keeping quality close to cloud-level.
Discussion (0). Continue with ORCID to comment.