neuralmagic
/

DeepSeek-R1-Distill-Qwen-1.5B-quantized.w8a8

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions Community

nm-research commited on Feb 20

Commit

5a39a4c

·

verified ·

1 Parent(s): a29146a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -285,7 +285,7 @@ lm_eval \
 ## Inference Performance
-This model achieves up to 1.14x speedup in single-stream deployment, depending on hardware and use-case scenario.
 The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.6.7.2, and [GuideLLM](https://github.com/neuralmagic/guidellm).
 <details>

 ## Inference Performance
+This model achieves up to 1.2x speedup in single-stream deployment, depending on hardware and use-case scenario.
 The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.6.7.2, and [GuideLLM](https://github.com/neuralmagic/guidellm).
 <details>