[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (#5543)

Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Signed-off-by: [Your Name] <your.email@example.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Bo Li <22713281+bobboli@users.noreply.github.com>
This commit is contained in:
authored and GitHub committed 2026-09-02 15:39:49 +00:00
1 parent d5fd9eb6bb
commit 95a9311696
77 files changed
+3470 -1077

No files matched your search

@@ -50,9 +50,6 @@ from tests.dfx.conftest import (
)
from tests.helpers.runtime import get_open_port
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
os.environ.setdefault("DIFFUSION_ATTENTION_BACKEND", "FLASH_ATTN")
# ---------------------------------------------------------------------------
# Inline field processing
@@ -837,7 +834,7 @@ def run_benchmark(
"Quantization": _to_quantization_value(server_type, serve_args_dict),
"offload": _to_offload_string(server_type, serve_args_dict),
"compile": _to_compile_value(server_type, serve_args_dict),
"Attn_backend": os.environ.get("DIFFUSION_ATTENTION_BACKEND", ""),
"Attn_backend": str(serve_args_dict.get("diffusion-attention-backend") or ""),
"num_inference_steps": params.get("num-inference-steps", ""),
"completed": completed,
"failed": failed,