[LoRA] Cleanup LoRA unused code (#29611)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Jee Jee Li
2025-11-28 22:52:58 -08:00
committed by GitHub
co-authored by Cyrus Leung
parent 4a80ad0a25
commit 39e63dec7c
46 changed files with 126 additions and 173 deletions
+1 -5
View File
@@ -34,12 +34,10 @@ class WorkerLoRAManager:
vllm_config: VllmConfig,
device: torch.device,
embedding_modules: dict[str, str],
embedding_padding_modules: list[str],
lora_model_cls: type[LoRAModel] = LoRAModel,
):
self._lora_model_cls = lora_model_cls
self.embedding_modules = embedding_modules
self.embedding_padding_modules = embedding_padding_modules
self._cached_dummy_lora: None | Literal[False] | LoRAModel = False
self.max_num_seqs = vllm_config.scheduler_config.max_num_seqs
self.max_num_batched_tokens = (
@@ -121,9 +119,7 @@ class WorkerLoRAManager:
lora_model_id=lora_request.lora_int_id,
device="cpu",
dtype=self.lora_config.lora_dtype,
target_embedding_padding=self.vocab_size,
embedding_modules=self.embedding_modules,
embedding_padding_modules=self.embedding_padding_modules,
model_vocab_size=self.vocab_size,
tensorizer_config_dict=lora_request.tensorizer_config_dict,
weights_mapper=hf_to_vllm_mapper,
)