SwiftKV

The Snowflake AI Research team is releasing a series of SwiftKV optimized Llama-3.1 models. SwiftKV is a series of inference optimizations that goes beyond traditional key-value (KV) cache compression. This method reduces computational overhead during prompt processing by combining model rewiring and knowledge-preserving self-distillation, allowing prefill tokens to skip up to half the model's layers. SwiftKV achieves up to 2x improvements in throughput, latency, and cost efficiency with minimal accuracy loss, making LLM deployments more performant and economically viable.

For more details about SwiftKV and how to use it:

Performance Metrics

To evaluate SwiftKV’s performance, we focus on the following key metrics (see more details in our blog):

  • Combined throughput: The total number of input and output tokens processed per second. This determines:
    • For batch processing, the time required to complete jobs.
    • For interactive use, the volume of concurrent requests a system can handle.
  • TTFT: The latency between a user request and receiving the first token in the response.
  • TPOT: The latency between subsequent tokens after the first token.

Combined input and output throughput for Llama 3.1 70B (left) and Llama 3.1 405B (right) across a range of input lengths (bottom). performance plot of llama-405B w. swiftkv

TTFT (top) and TPOT (bottom) for input lengths 2000 (left), 8000 (middle), and 32000 (right) for Llama 3.1 405B fp8 model. For each experiment, a range of different request arrival rates is simulated. Each request generates 256 output tokens. performance plot of llama-405B w. swiftkv

Eval Metrics

For a full breakdown on evaluation metrics and performance impact please refer to our blog and arXiv paper but below we've outlined some relevant evaluation metrics.

Llama-3.1-405B-Instruct-FP8 Arc Challenge Winogrande HellaSwag TruthfulQA MMLU MMLU cot GSM8K Avg
Baseline 94.7 87.0 88.3 64.7 87.5 88.1 96.1 86.6
50% SingleInputKV 94.0 86.3 88.1 64.2 85.7 87.5 95.2 85.9
Llama-3.1-8B-Instruct Arc Challenge Winogrande HellaSwag TruthfulQA MMLU MMLU cot GSM8K Avg
Baseline 82.00 77.90 80.40 54.56 67.90 70.63 82.56 73.71
50% SingleInputKV 80.38 78.22 79.30 54.54 67.30 69.73 79.45 72.70

Get started by serving SwiftKV on vLLM

Instructions on how to use vLLM for both evaluation and performance benchmarks: https://github.com/Snowflake-Labs/vllm/tree/swiftkv/examples/swiftkv

Downloads last month
74
Safetensors
Model size
425B params
Tensor type
BF16
·
F8_E4M3
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8

Quantized
(32)
this model

Collection including Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8