Organize Benchmark (#381)

benchmark/gsm8k/bench_other.py

@@ -5,17 +5,11 @@ import json
 import re
 import time
 from concurrent.futures import ThreadPoolExecutor
-from functools import partial
 
 import numpy as np
 from tqdm import tqdm
 
-from sglang.test.test_utils import (
-    add_common_other_args_and_parse,
-    call_generate_lightllm,
-    call_generate_srt_raw,
-    call_generate_vllm,
-)
+from sglang.test.test_utils import add_common_other_args_and_parse, get_call_generate
 from sglang.utils import dump_state_text, read_jsonl
 
 INVALID = -9999999
@@ -63,54 +57,7 @@ def main(args):
     states = [None] * len(labels)
 
     # Select backend
-    if args.backend == "lightllm":
-        url = f"{args.host}:{args.port}/generate"
-        call_generate = partial(call_generate_lightllm, url=url)
-    elif args.backend == "vllm":
-        url = f"{args.host}:{args.port}/generate"
-        call_generate = partial(call_generate_vllm, url=url)
-    elif args.backend == "srt-raw":
-        url = f"{args.host}:{args.port}/generate"
-        call_generate = partial(call_generate_srt_raw, url=url)
-    elif args.backend == "guidance":
-        from guidance import gen, models
-
-        model = models.LlamaCpp(
-            "/home/ubuntu/model_weights/Llama-2-7b-chat.gguf",
-            n_gpu_layers=-1,
-            n_ctx=4096,
-        )
-
-        def call_generate(prompt, temperature, max_tokens, stop):
-            out = (
-                model
-                + prompt
-                + gen(
-                    name="answer",
-                    max_tokens=max_tokens,
-                    temperature=temperature,
-                    stop=stop,
-                )
-            )
-            return out["answer"]
-
-    elif args.backend == "lmql":
-        import lmql
-
-        model = lmql.model(args.model_path, endpoint=f"{args.host}:{args.port}")
-
-        @lmql.query(model=model)
-        async def program(question):
-            '''lmql
-            """{question}[ANSWER]""" where len(TOKENS(ANSWER)) < 257 and STOPS_AT(ANSWER, "Question")
-            return ANSWER
-            '''
-
-        async def call_generate(prompt, temperature, max_tokens, stop):
-            return await program(question=prompt, temperature=0)
-
-    else:
-        raise ValueError(f"Invalid backend: {args.backend}")
+    call_generate = get_call_generate(args)
 
     # Run requests
     if args.backend != "lmql":
@@ -130,7 +77,13 @@ def main(args):
                 get_one_answer(i)
         else:
             with ThreadPoolExecutor(args.parallel) as executor:
-                executor.map(get_one_answer, list(range(len(questions))))
+                list(
+                    tqdm(
+                        executor.map(get_one_answer, list(range(len(questions)))),
+                        total=len(questions),
+                    )
+                )
+
     else:
         # Use asyncio
         async def batched_call(batch_size):