biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc] Improve LoRA spelling (#13831)

Browse Source
This commit is contained in:
Jee Jee Li
2025-02-26 15:43:01 +08:00
committed by GitHub
parent e206b54331
commit 5157338ed9
25 changed files with 80 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/entrypoints/openai/api_server.py
View File

@@ -53,7 +53,7 @@ from vllm.entrypoints.openai.protocol import (ChatCompletionRequest,
EmbeddingResponse,
EmbeddingResponseData,
ErrorResponse,
LoadLoraAdapterRequest,
LoadLoRAAdapterRequest,
PoolingChatRequest,
PoolingCompletionRequest,
PoolingRequest, PoolingResponse,
@@ -63,7 +63,7 @@ from vllm.entrypoints.openai.protocol import (ChatCompletionRequest,
TokenizeResponse,
TranscriptionRequest,
TranscriptionResponse,
UnloadLoraAdapterRequest)
UnloadLoRAAdapterRequest)
from vllm.entrypoints.openai.reasoning_parsers import ReasoningParserManager
# yapf: enable
from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
@@ -690,12 +690,12 @@ if envs.VLLM_TORCH_PROFILER_DIR:
if envs.VLLM_ALLOW_RUNTIME_LORA_UPDATING:
logger.warning(
"Lora dynamic loading & unloading is enabled in the API server. "
"LoRA dynamic loading & unloading is enabled in the API server. "
"This should ONLY be used for local development!")
@router.post("/v1/load_lora_adapter",
dependencies=[Depends(validate_json_request)])
async def load_lora_adapter(request: LoadLoraAdapterRequest,
async def load_lora_adapter(request: LoadLoRAAdapterRequest,
raw_request: Request):
handler = models(raw_request)
response = await handler.load_lora_adapter(request)
@@ -707,7 +707,7 @@ if envs.VLLM_ALLOW_RUNTIME_LORA_UPDATING:
@router.post("/v1/unload_lora_adapter",
dependencies=[Depends(validate_json_request)])
async def unload_lora_adapter(request: UnloadLoraAdapterRequest,
async def unload_lora_adapter(request: UnloadLoRAAdapterRequest,
raw_request: Request):
handler = models(raw_request)
response = await handler.unload_lora_adapter(request)