[Model] Add Inkling LoRA support [4/N] (#48884)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
Woosuk Kwon
2026-07-17 09:52:15 +08:00
committed by GitHub
co-authored by Bugen Zhao Giancarlo Delfin Isotr0py Isotr0py Jee Jee Li Roger Wang Yifan Qiao Claude Fable 5 OpenAI Codex
parent fe784ff22e
commit f3e9497e92
12 changed files with 337 additions and 47 deletions
+6
View File
@@ -602,6 +602,7 @@ class EngineArgs:
enable_tower_connector_lora: bool = LoRAConfig.enable_tower_connector_lora
specialize_active_lora: bool = LoRAConfig.specialize_active_lora
enable_mixed_moe_lora_format: bool = LoRAConfig.enable_mixed_moe_lora_format
enable_moe_shared_loras: bool = LoRAConfig.enable_moe_shared_loras
ray_workers_use_nsight: bool = ParallelConfig.ray_workers_use_nsight
num_gpu_blocks_override: int | None = CacheConfig.num_gpu_blocks_override
@@ -1351,6 +1352,10 @@ class EngineArgs:
"--enable-mixed-moe-lora-format",
**lora_kwargs["enable_mixed_moe_lora_format"],
)
lora_group.add_argument(
"--enable-moe-shared-loras",
**lora_kwargs["enable_moe_shared_loras"],
)
# Observability arguments
observability_kwargs = get_kwargs(ObservabilityConfig)
@@ -2213,6 +2218,7 @@ class EngineArgs:
enable_tower_connector_lora=self.enable_tower_connector_lora,
specialize_active_lora=self.specialize_active_lora,
enable_mixed_moe_lora_format=self.enable_mixed_moe_lora_format,
enable_moe_shared_loras=self.enable_moe_shared_loras,
max_cpu_loras=self.max_cpu_loras
if self.max_cpu_loras and self.max_cpu_loras > 0
else None,