[BugFix] fix(omni): isolate diffusion KV-cache dtype from vLLM --kv-cache-dtype #3585 (#3596)

Signed-off-by: lyj-jjj <liuyingjun5@huawei.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
lyj-jjjandCursor authored and GitHub committed 2026-05-15 11:22:59 +08:00
1 parent adb2291c27
commit bbc00f9f86
6 files changed
+104 -78

No files matched your search

+12 -13
View File
@@ -472,26 +472,25 @@ class OmniServeCommand(CLISubcommand):
default=None,
help="Scheduler flow_shift for video models (e.g., 5.0 for 720p, 12.0 for 480p).",
)
# vLLM already registers --kv-cache-dtype for the serve parser. Keep
# this fallback only for older vLLM versions where the option is absent.
if "--kv-cache-dtype" not in serve_parser._option_string_actions:
omni_config_group.add_argument(
"--kv-cache-dtype",
type=str,
default=None,
help="Config-level KV cache dtype (e.g. fp8).",
)
# Diffusion KV-cache quantization uses dedicated flags so we do not reuse
# vLLM's --kv-cache-dtype (AR cache dtype, default "auto").
omni_config_group.add_argument(
"--kv-cache-skip-steps",
"--diffusion-kv-cache-dtype",
type=str,
default=None,
help="Config-level KV-cache quantization skip-step selector, e.g. '0-9,20,25-30'.",
help="Diffusion attention KV cache dtype (e.g. fp8). Separate from vLLM --kv-cache-dtype.",
)
omni_config_group.add_argument(
"--kv-cache-skip-layers",
"--diffusion-kv-cache-skip-steps",
type=str,
default=None,
help="Config-level KV-cache quantization skip-layer selector, e.g. '0,1,4-8'.",
help="Diffusion KV-cache quantization skip-step selector, e.g. '0-9,20,25-30'.",
)
omni_config_group.add_argument(
"--diffusion-kv-cache-skip-layers",
type=str,
default=None,
help="Diffusion KV-cache quantization skip-layer selector, e.g. '0,1,4-8'.",
)
omni_config_group.add_argument(
"--cfg-parallel-size",