42 lines
1.2 KiB
Python
42 lines
1.2 KiB
Python
from __future__ import annotations
|
|
|
|
VLLM_GPU_ALIASES = {
|
|
"910b": ["Ascend_910-b3", "Ascend_910-b4"],
|
|
"s4000": ["Mthreads_s4000"],
|
|
"k100": ["hygon_k100-ai"],
|
|
"mrv100": ["Iluvatar_mrv-100"],
|
|
"bi100": ["Iluvatar_bi-100"],
|
|
"bi150": ["Iluvatar_bi-150"],
|
|
"c500": ["MetaX_c-500"],
|
|
"mlu370-x4": ["Cambricon_mlu-370-x4"],
|
|
"mlu370-x8": ["Cambricon_mlu-370-x8"],
|
|
"p800": ["Kunlunxin_p-800"],
|
|
"166m": ["Biren_166m"],
|
|
"biren166m": ["Biren_166m"], # backward-compatible alias from the old config.py
|
|
}
|
|
|
|
# Sunrise s2 currently uses SGLang in the old config, so vLLM-only v1 skips it.
|
|
UNSUPPORTED_VLLM_ALIASES = {"s2"}
|
|
|
|
|
|
def parse_aliases(raw: str | None, defaults: list[str]) -> list[str]:
|
|
if not raw:
|
|
return defaults
|
|
return [item.strip() for item in raw.split(",") if item.strip()]
|
|
|
|
|
|
def expand_gpu_alias(alias: str) -> list[str]:
|
|
return VLLM_GPU_ALIASES.get(alias, [])
|
|
|
|
|
|
def expand_gpu_aliases(aliases: list[str]) -> list[tuple[str, str]]:
|
|
pairs: list[tuple[str, str]] = []
|
|
for alias in aliases:
|
|
for gpu_type in expand_gpu_alias(alias):
|
|
pairs.append((alias, gpu_type))
|
|
return pairs
|
|
|
|
|
|
def is_supported_alias(alias: str) -> bool:
|
|
return alias in VLLM_GPU_ALIASES
|