[RFC] Replace shared-memory routed experts with ModelRunnerOutput transfer and HTTP support (#39568)
Signed-off-by: xhx1022 <1737006628@qq.com> Signed-off-by: arlenxu <arlenxu@tencent.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Co-authored-by: arlenxu <arlenxu@tencent.com> Co-authored-by: Junjie Zhang <junj.jay.zhang@gmail.com>
This commit is contained in:
co-authored by
Claude Opus 4.6
arlenxu
Junjie Zhang
parent
2317682f95
commit
c7560af424
@@ -785,6 +785,30 @@ class VllmConfig:
|
||||
|
||||
self.parallel_config.is_moe_model = self.model_config.is_moe
|
||||
|
||||
if (
|
||||
self.model_config is not None
|
||||
and self.model_config.enable_return_routed_experts
|
||||
):
|
||||
if self.parallel_config.pipeline_parallel_size > 1:
|
||||
raise ValueError(
|
||||
"--enable-return-routed-experts is incompatible with "
|
||||
"pipeline parallelism (PP > 1)."
|
||||
)
|
||||
|
||||
# Incompatible with any KV connector — covers both PD disaggregation
|
||||
# (kv_producer/kv_consumer: routing captured on P can't reach D) and
|
||||
# single-instance KV offload/sharing (kv_both: slot_mapping semantics
|
||||
# change when KV blocks live outside local GPU memory, breaking the
|
||||
# slot-indexed routed_experts buffer).
|
||||
if (
|
||||
self.kv_transfer_config is not None
|
||||
and self.kv_transfer_config.is_kv_transfer_instance
|
||||
):
|
||||
raise ValueError(
|
||||
"--enable-return-routed-experts is incompatible with KV "
|
||||
"connectors (PD disaggregation, KV cache offload)."
|
||||
)
|
||||
|
||||
if self.lora_config is not None:
|
||||
self.lora_config.verify_with_model_config(self.model_config)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user