[refactor] Read resolved config from server_args fields; retire the flags mirror tier (#30346)

This commit is contained in:
Cheng Wan
2026-07-07 21:28:34 -07:00
committed by GitHub
parent b14f7b4f75
commit be32c57598
60 changed files with 238 additions and 795 deletions
@@ -102,10 +102,6 @@ def _make_model_runner(
sa = SimpleNamespace()
sa.swa_full_tokens_ratio = swa_full_tokens_ratio
# The configurator reads the resolved ratio from the flags tier.
from sglang.srt.runtime_context import get_flags
get_flags().swa_full_tokens_ratio = swa_full_tokens_ratio
sa.page_size = page_size
sa.disable_radix_cache = disable_radix_cache
sa.chunked_prefill_size = chunked_prefill_size