diff --git a/fastchat/serve/base_model_worker.py b/fastchat/serve/base_model_worker.py
index 2fe322990..a83da3d44 100644
--- a/fastchat/serve/base_model_worker.py
+++ b/fastchat/serve/base_model_worker.py
@@ -215,7 +215,7 @@ async def api_generate(request: Request):
 async def api_get_embeddings(request: Request):
     params = await request.json()
     await acquire_worker_semaphore()
-    embedding = worker.get_embeddings(params)
+    embedding = await asyncio.to_thread(worker.get_embeddings, params)
     release_worker_semaphore()
     return JSONResponse(content=embedding)
 
diff --git a/fastchat/serve/huggingface_api_worker.py b/fastchat/serve/huggingface_api_worker.py
index 6ed8e6c8c..e7f19b05b 100644
--- a/fastchat/serve/huggingface_api_worker.py
+++ b/fastchat/serve/huggingface_api_worker.py
@@ -233,7 +233,7 @@ async def api_generate(request: Request):
     params = await request.json()
     worker = worker_map[params["model"]]
     await acquire_worker_semaphore(worker)
-    output = worker.generate_gate(params)
+    output = await asyncio.to_thread(worker.generate_gate, params)
     release_worker_semaphore(worker)
     return JSONResponse(output)
 
diff --git a/fastchat/serve/multi_model_worker.py b/fastchat/serve/multi_model_worker.py
index 5e6266fe0..362caea44 100644
--- a/fastchat/serve/multi_model_worker.py
+++ b/fastchat/serve/multi_model_worker.py
@@ -109,7 +109,7 @@ async def api_generate(request: Request):
     params = await request.json()
     await acquire_worker_semaphore()
     worker = worker_map[params["model"]]
-    output = worker.generate_gate(params)
+    output = await asyncio.to_thread(worker.generate_gate, params)
     release_worker_semaphore()
     return JSONResponse(output)