227ef603a6
- Restructure repo around experiments/<name>/ and platforms/<chip>.env. - Add shared scripts under scripts/common/ for platform/server/bench-client logic. - Add Kunlun P800 platform config and runtime patches. - Add dsv4_p800_sglang experiment with INT8 smoke-test support. - Update BENCHMARK_WORKFLOW.md and README.md with chip/engine recording rules. - Add scripts/analysis/compare_experiments.py for cross-experiment comparison. - Ignore experiments/*/results/ raw output directories by default.
19 lines
541 B
Bash
19 lines
541 B
Bash
# Platform configuration for NVIDIA H200
|
|
# Source this file via scripts/common/platform.sh
|
|
|
|
CHIP="nvidia_h200"
|
|
ACCELERATOR="NVIDIA H200"
|
|
HARDWARE="8x NVIDIA H200 143GB"
|
|
|
|
# Device selection
|
|
DEVICE_SELECT_ENV="CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7"
|
|
CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
|
|
|
|
# Default serving port and model root on the host
|
|
DEFAULT_PORT="30004"
|
|
MODEL_ROOT="/data/models"
|
|
|
|
# Virtual environments on the host (used by native H200 scripts)
|
|
VENV_VLLM_DSPARK="/data/user1/yy/envs/vllm-dspark"
|
|
VENV_SGLANG="/data/user1/yy/envs/sglang"
|