Report median instead of mean in bench_latency.py (#1269)

This commit is contained in:
Lianmin Zheng
2024-08-30 06:05:01 -07:00
committed by GitHub
parent 55f5976b42
commit 79ece2c51f
3 changed files with 8 additions and 14 deletions

View File

@@ -233,7 +233,6 @@ python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct
### Supported Models
**Generative Models**
- Exaone 3.0
- Llama / Llama 2 / Llama 3 / Llama 3.1
- Mistral / Mixtral / Mistral NeMo
- Gemma / Gemma 2
@@ -253,6 +252,7 @@ python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct
- Grok
- ChatGLM
- InternLM 2
- Exaone 3
**Embedding Models**