[Perf] Support minimum KV splits configuration for TokenSpeed MLA decode (#60345)

Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
This commit is contained in:
Wei Zhao
2026-10-09 23:33:47 +00:00
committed by GitHub
co-authored by Codex
parent 04b02fc8a5
commit 03a7d3776f
4 changed files with 83 additions and 22 deletions
+6
View File
@@ -503,6 +503,12 @@ def test_attention_config():
engine_args = EngineArgs.from_cli_args(args)
assert engine_args.attention_config == AttentionConfig()
args = parser.parse_args(
["--attention-config", '{"tokenspeed_mla_min_split_kv": 8}']
)
engine_args = EngineArgs.from_cli_args(args)
assert engine_args.attention_config.tokenspeed_mla_min_split_kv == 8
# set backend via dot notation
args = parser.parse_args(["--attention-config.backend", "FLASH_ATTN"])
assert args is not None