REVIEW 3 cited by
Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
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
read the original abstract
With the fast growth of parameter size, it becomes increasingly challenging to deploy large generative models as they typically require large GPU memory consumption and massive computation. Unstructured model pruning has been a common approach to reduce both GPU memory footprint and the overall computation while retaining good model accuracy. However, the existing solutions do not provide a highly-efficient support for handling unstructured sparsity on modern GPUs, especially on the highly-structured Tensor Core hardware. Therefore, we propose Flash-LLM for enabling low-cost and highly-efficient large generative model inference with the sophisticated support of unstructured sparsity on high-performance but highly restrictive Tensor Cores. Based on our key observation that the main bottleneck of generative model inference is the several skinny matrix multiplications for which Tensor Cores would be significantly under-utilized due to low computational intensity, we propose a general Load-as-Sparse and Compute-as-Dense methodology for unstructured sparse matrix multiplication. The basic insight is to address the significant memory bandwidth bottleneck while tolerating redundant computations that are not critical for end-to-end performance on Tensor Cores. Based on this, we design an effective software framework for Tensor Core based unstructured SpMM, leveraging on-chip resources for efficient sparse data extraction and computation/memory-access overlapping. At SpMM kernel level, Flash-LLM significantly outperforms the state-of-the-art library, i.e., Sputnik and SparTA by an average of 2.9x and 1.5x, respectively. At end-to-end framework level on OPT-30B/66B/175B models, for tokens per GPU-second, Flash-LLM achieves up to 3.8x and 3.6x improvement over DeepSpeed and FasterTransformer, respectively, with significantly lower inference cost.
Forward citations
Cited by 3 Pith papers
-
Celty: SpMspV GPU Kernel and SIMT Co-Design for Efficient Dual-Sparse LLM Inference
Dual-sparse LLM decoding can be accelerated by an RLC-CSC spMspV kernel, and a small SIMT-core hardware addition is proposed to remove the remaining index-reconstruction and accumulation bottlenecks.
-
Sparsity-Aware Low-Rank Representation for Efficient Fine-Tuning of Large Language Models
SALR combines static pruning of frozen weights with a trainable truncated-SVD low-rank residual adapter to match LoRA accuracy at 50% sparsity, cutting model size ~2x and giving ~1.7x inference speedup.
-
SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters
Sharing one MLP layer's weights across several layers plus low-rank adapters recovers most of a pretrained LLM's quality with a fraction of the storage and faster phone inference.
Discussion (0). Continue with ORCID to comment.