[Core] Relax the LoRA max rank (vllm-project#26461)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: 0xrushi <6279035+0xrushi@users.noreply.github.com>

Author: jeejeelee

vllm/config/lora.py

@@ -103,7 +103,7 @@ def __post_init__(self):
 
         # Setting the maximum rank to 512 should be able to satisfy the vast
         # majority of applications.
-        possible_max_ranks = (8, 16, 32, 64, 128, 256, 320, 512)
+        possible_max_ranks = (1, 8, 16, 32, 64, 128, 256, 320, 512)
         possible_lora_extra_vocab_size = (256, 512)
         if self.max_lora_rank not in possible_max_ranks:
             raise ValueError(

vllm/v1/worker/lora_model_runner_mixin.py

@@ -28,8 +28,6 @@
 
 # Defined as a mixin for GPUModelRunner
 class LoRAModelRunnerMixin:
-    LORA_WARMUP_RANK = 8
-
     def load_lora_model(
         self, model: nn.Module, vllm_config: VllmConfig, device: torch.device
     ) -> nn.Module:
@@ -96,7 +94,9 @@ def maybe_setup_dummy_loras(
             assert self.lora_manager is not None, "LoRA is not enabled"
 
             num_loras = lora_config.max_loras
-
+            lora_warmup_rank = (
+                lora_config.max_lora_rank if lora_config.max_lora_rank < 8 else 8
+            )
             # Make dummy lora requests
             lora_requests: set[LoRARequest] = {
                 LoRARequest(
@@ -111,7 +111,7 @@ def maybe_setup_dummy_loras(
                 # Add the dummy LoRAs here so _set_active_loras doesn't try to
                 # load from disk.
                 for lr in lora_requests:
-                    self.lora_manager.add_dummy_lora(lr, rank=self.LORA_WARMUP_RANK)
+                    self.lora_manager.add_dummy_lora(lr, rank=lora_warmup_rank)
 
                 yield