sglangv0.5.2 & support Qwen3-Next-80B-A3B-Instruct

2025-09-13 17:00:20 +08:00
commit 118f1fc726
2037 changed files with 515371 additions and 0 deletions
--- a/benchmark/json_schema/README.md
+++ b/benchmark/json_schema/README.md
@@ -0,0 +1,15 @@
+## Run benchmark
+
+### Benchmark sglang
+
+Run Llama-8b
+
+```bash
+python3 -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --port 30000
+```
+
+Benchmark
+
+```bash
+python3 bench_sglang.py
+```