8ebe963269
- New experiment directory with adaptive concurrency benchmark for SGLang - Platform config for 8x NVIDIA RTX 6000D 84GB - Adapted from dsv4_h200_sglang_tp_dp_matrix with updated paths: - Model path: /data/hf_models/DeepSeek-V4-Flash - Venv path: /root/.miniconda3/envs/sglang - Dataset path: /data/yy/sskj/datasets/
Platform Configurations
Each .env file in this directory describes one accelerator platform.
They are meant to be sourced by benchmark scripts through
scripts/common/platform.sh, not executed directly.
Usage
# Default platform for the current machine
bash experiments/dsv4_p800_sglang/run_bench.sh
# Explicitly select a platform
PLATFORM=kunlun_p800 bash experiments/dsv4_p800_sglang/run_bench.sh
Current platforms
| File | Chip/Accelerator | Engine | Notes |
|---|---|---|---|
kunlun_p800.env |
Kunlun P800 XPU | sglang-xpu |
Docker-based SGLang serving image |
nvidia_h200.env |
NVIDIA H200 | vllm-dspark |
Native host virtual environments |
What belongs here
- Chip/accelerator identity (
CHIP,ACCELERATOR,HARDWARE,ENGINE). - Device selection environment variables.
- Platform-wide paths that rarely change (model root, default port).
- Container image / interpreter paths for Docker-based platforms.
- Native interpreter / venv paths for host-based platforms.
What does NOT belong here
- Specific model names or experiment scenarios — those go in
experiments/<name>/config.env. - Engine-specific launch flags — those go in the experiment's
start_server.shorrun_bench.sh.
Adding a new platform
- Create
platforms/<chip>.envwith at leastCHIP,ACCELERATOR,HARDWARE,ENGINE,DEFAULT_PORT,MODEL_ROOT. - If the platform runs inside Docker, set
DOCKER_IMAGE,CONTAINER_NAME,CONTAINER_PYTHON, andPATCH_ROOT(seekunlun_p800.env). - If the platform runs natively on the host, set the relevant venv paths
(see
nvidia_h200.env). - Add a row to the table above and write a quick-start experiment under
experiments/<name>/.