Add typo checker in pre-commit (#6179)

Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>

benchmark/hicache/bench_serving.py

@@ -267,7 +267,7 @@ async def get_requests(
         try:
             request = await asyncio.wait_for(
                 input_requests_queue.get(), timeout=300
-            )  # Wait for 5 minites then abort
+            )  # Wait for 5 minutes then abort
         except Exception as e:
             print(f"exception: {e}")
             break
@@ -514,7 +514,7 @@ async def benchmark(
     print("{:<40} {:<10}".format("Traffic request rate:", request_rate))
     print(
         "{:<40} {:<10}".format(
-            "Max reqeuest concurrency:",
+            "Max request concurrency:",
             max_concurrency if max_concurrency else "not set",
         )
     )

benchmark/json_schema/bench_sglang.py

@@ -95,7 +95,7 @@ def bench_schema(args):
     latency = time.time() - tic
 
     # Check if the outputs are valid
-    indexs = []
+    indexes = []
     for i, state in enumerate(states):
         try:
             schema = json.loads(arguments[i]["json_schema"])
@@ -103,7 +103,7 @@ def bench_schema(args):
             assert jsonschema.validate(obj, schema) is None
         except Exception as e:
             print(e)
-            indexs.append(i)
+            indexes.append(i)
 
     return states, latency
 

benchmark/line_retrieval/gen_data.py

@@ -15,7 +15,7 @@ from tqdm import tqdm
 
 def generate_lines(random_words, num_lines, redirect_ratio):
     prefix = "Here is a list of lines, each with its corresponding REGISTER_CONTENT value. Please memorize them. Be prepared to provide the REGISTER_CONTENT value for a specific line index when I ask."
-    suffix = "The list has ended. Please give the final REGISTER_CONTENT value for a specific line after resovling the redirections and references. For example, the REGISTER_CONTENT of Line __idx0__ is __val0__. The REGISTER_CONTENT of Line __idx1__ is __val1__. The REGISTER_CONTENT of Line __idx2__ is __val2__. The REGISTER_CONTENT of Line ??? is"
+    suffix = "The list has ended. Please give the final REGISTER_CONTENT value for a specific line after resolving the redirections and references. For example, the REGISTER_CONTENT of Line __idx0__ is __val0__. The REGISTER_CONTENT of Line __idx1__ is __val1__. The REGISTER_CONTENT of Line __idx2__ is __val2__. The REGISTER_CONTENT of Line ??? is"
 
     # Raw lines
     visited_indices = set([None])

benchmark/multi_document_qa/bench_other.py

@@ -17,7 +17,7 @@ ASSISTANT_SUFFIX = " </s><s>"
 
 def multi_document_qa(docs, question, generate):
     s = USER_PREFIX
-    s += "Pleaes answer a question according to given documents.\n"
+    s += "Please answer a question according to given documents.\n"
     s += "Question:" + question + "Documents begin.\n"
 
     s += "".join(docs)

benchmark/multi_document_qa/bench_sglang.py

@@ -13,7 +13,7 @@ from sglang.utils import dump_state_text, read_jsonl
 @sgl.function
 def multi_document_qa(s, docs, question):
     s += sgl.user_begin()
-    s += "Pleaes answer a question according to given documents.\n"
+    s += "Please answer a question according to given documents.\n"
     s += "Question:" + question + "Documents begin.\n"
 
     forks = s.fork(len(docs))