adapt to sglang v0.5.2rc1 on dcu

benchmark/generative_agents/bench_sglang.py

+import argparse
+import json
+import time
+
+from agent_functions import (
+    action_location_object,
+    action_location_sector,
+    generate_event_triple,
+    generate_pronunciatio,
+    poignancy_event,
+)
+
+import sglang as sgl
+from sglang.test.test_utils import (
+    add_common_sglang_args_and_parse,
+    select_sglang_backend,
+)
+from sglang.utils import dump_state_text, read_jsonl
+
+
+def main(args):
+    lines = read_jsonl(args.data_path)[: args.num_events]
+    mapping = {
+        "poignancy_event": poignancy_event,
+        "generate_event_triple": generate_event_triple,
+        "generate_pronunciatio": generate_pronunciatio,
+        "action_location_sector": action_location_sector,
+        "action_location_object": action_location_object,
+    }
+    arguments = [{mapping[k]: v for k, v in l.items()} for l in lines]
+
+    # Select backend
+    backend = select_sglang_backend(args)
+    sgl.set_default_backend(backend)
+
+    states = []
+    # Run requests
+    tic = time.perf_counter()
+    for a in arguments:
+        # only a single key in the dict
+        for func, arg in a.items():
+            result = func.run(**arg)
+        result.sync()
+        states.append(result)
+    latency = time.perf_counter() - tic
+
+    # Compute accuracy
+    print(f"Latency: {latency:.3f}")
+
+    # Write results
+    dump_state_text(f"tmp_output_{args.backend}.txt", states)
+
+    with open(args.result_file, "a") as fout:
+        value = {
+            "task": "Generative Agents",
+            "backend": args.backend,
+            "num_gpus": 1,
+            "latency": round(latency, 3),
+            # to pack weighted functions as a single agent
+            "num_requests": len(arguments) / len(mapping),
+            "other": {
+                "num_events": args.num_events,
+                "parallel": args.parallel,
+            },
+        }
+        fout.write(json.dumps(value) + "\n")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--data-path", type=str, default="agent_calls.jsonl")
+    parser.add_argument("--num-events", type=int, default=10)
+    args = add_common_sglang_args_and_parse(parser)
+    main(args)

benchmark/gpt_oss/README.md

+# How to reproduce the result of GPT-OSS with SGLang
+
+### Install the latest SGLang
+
+```bash
+git clone https://github.com/sgl-project/sglang.git
+cd sglang
+git checkout v0.5.1.post3
+
+pip install --upgrade pip
+pip install -e "python[all]"
+```
+
+### Reproduce the benchmark throughput result (Batch Size 1)
+
+Launch Command
+
+```bash
+# MXFP4 120B on H100
+python3 -m sglang.launch_server --model openai/gpt-oss-120b --tp 8 --attention-backend triton
+
+# BF16 120B on H100
+python3 -m sglang.launch_server --model lmsys/gpt-oss-120b-bf16 --tp 8 --attention-backend triton
+
+# MXFP4 120B on B200
+python3 -m sglang.launch_server --model openai/gpt-oss-120b --tp 4
+
+# BF16 120B on B200
+python3 -m sglang.launch_server --model lmsys/gpt-oss-120b-bf16 --tp 4
+```
+
+Benchmark Command
+
+```bash
+
+# MXFP4 120B on H100
+python3 -m sglang.bench_one_batch_server --model openai/gpt-oss-120b --base-url http://localhost:30000 --batch-size 1 --input-len 1024 --output-len 512 --show-report
+```
+
+### Reproduce the benchmark throughput result (Batch Size 32)
+
+Launch Command
+
+```bash
+# MXFP4 120B on H100
+python3 -m sglang.launch_server --model openai/gpt-oss-120b --tp 8
+
+# BF16 120B on H100
+python3 -m sglang.launch_server --model lmsys/gpt-oss-120b-bf16 --tp 8
+
+# MXFP4 120B on B200
+python3 -m sglang.launch_server --model openai/gpt-oss-120b --tp 4
+
+# BF16 120B on B200
+python3 -m sglang.launch_server --model lmsys/gpt-oss-120b-bf16 --tp 4
+```
+
+Benchmark Command
+
+```bash
+python3 -m sglang.bench_one_batch_server --model openai/gpt-oss-120b --base-url http://localhost:30000 --batch-size 32 --input-len 1024 8192 --output-len 512 --show-report
+```
+
+### Reproduce the evaluation result
+
+Install gpt-oss
+
+```bash
+git clone https://github.com/openai/gpt-oss.git
+cd gpt-oss
+pip install -e .
+```
+
+Evaluation Command
+
+```bash
+DATASET=gpqa
+BASE_URL=YOUR_BASE_URL
+OPENAI_API_KEY=dummy python -m gpt_oss.evals \
+    --base-url ${BASE_URL}/v1 \
+    --model dummy \
+    --reasoning-effort low,medium,high \
+    --eval $DATASET \
+    --n-threads 1000
+```
+
+### Reproduce the benchmark result of acceptance length
+> Note: On B200, if top k is 1, set `--attention-backend trtllm_mha`
+```bash
+git clone https://github.com/sgl-project/SpecForge.git
+cd SpecForge/benchmarks
+config_list=(
+    "1,0,0,0"
+    "1,3,1,4"
+    "1,5,4,8"
+)
+python3 bench_model_speedup.py \
+    --model-path openai/gpt-oss-120b \
+    --speculative-draft-model-path lmsys/EAGLE3-gpt-oss-120b-bf16 \
+    --port 20001 \
+    --trust-remote-code \
+    --mem-fraction-static 0.8 \
+    --tp-size 4 \
+    --attention-backend fa3 \
+    --config-list "${config_list[@]}" \
+    --benchmark-list mtbench:80 gsm8k:200 humaneval:200 math500:200 \
+    --output lmsys_gpt-oss-120b_Eagle3_result.jsonl
+
+python3 bench_model_speedup.py \
+    --model-path openai/gpt-oss-120b \
+    --speculative-draft-model-path nvidia/gpt-oss-120b-Eagle3 \
+    --port 20001 \
+    --trust-remote-code \
+    --mem-fraction-static 0.8 \
+    --tp-size 4 \
+    --attention-backend fa3 \
+    --config-list "${config_list[@]}" \
+    --benchmark-list mtbench:80 gsm8k:200 humaneval:200 math500:200 \
+    --output nv_gpt-oss-120b_Eagle3_result.jsonl
+```
+
+### Reproduce the result of speculative decoding speedup
+
+Launch Command
+
+```bash
+# On Hopper:
+# - Tree decoding (topk > 1) and chain decoding (topk = 1) are supported on both FA3 and Triton backends.
+python3 -m sglang.launch_server --model openai/gpt-oss-120b --speculative-algorithm EAGLE3 --speculative-draft-model-path lmsys/EAGLE3-gpt-oss-120b-bf16 --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --tp 4
+python3 -m sglang.launch_server --model openai/gpt-oss-120b --speculative-algorithm EAGLE3 --speculative-draft-model-path lmsys/EAGLE3-gpt-oss-120b-bf16 --speculative-num-steps 5 --speculative-eagle-topk 4 --speculative-num-draft-tokens 8 --tp 4
+
+# On Blackwell:
+# - Chain decoding (topk = 1) is supported on TRTLLM-MHA backend. Tree decoding (topk > 1) is in progress, stay tuned!
+# - Both tree decoding (topk > 1) and chain decoding (topk = 1) are supported on the Triton backend.
+python3 -m sglang.launch_server --model openai/gpt-oss-120b --speculative-algo EAGLE3 --speculative-draft lmsys/EAGLE3-gpt-oss-120b-bf16 --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --tp 4
+python3 -m sglang.launch_server --model openai/gpt-oss-120b --speculative-algo EAGLE3 --speculative-draft lmsys/EAGLE3-gpt-oss-120b-bf16 --speculative-num-steps 5 --speculative-eagle-topk 4 --speculative-num-draft-tokens 8 --attention-backend triton --tp 4
+```
+
+Benchmark Command
+
+```bash
+config_list=(
+    "1,0,0,0"
+    "1,3,1,4"
+    "1,5,4,8"
+)
+python3 bench_model_speedup.py \
+    --model-path openai/gpt-oss-120b \
+    --speculative-draft-model-path lmsys/EAGLE3-gpt-oss-120b-bf16 \
+    --port 20001 \
+    --trust-remote-code \
+    --mem-fraction-static 0.8 \
+    --tp-size 4 \
+    --attention-backend fa3 \
+    --config-list "${config_list[@]}" \
+    --benchmark-list gsm8k:200 humaneval:200 math500:200 \
+    --output lmsys_gpt-oss-120b_Eagle3_result.jsonl
+```
+
+We can gain the best speedup with the following settings:
+
+- **1.39x** speedup with the `--speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4` setting.
+- **1.52x** speedup with the `--speculative-num-steps 5 --speculative-eagle-topk 4 --speculative-num-draft-tokens 8` setting.

benchmark/gsm8k/README.md

+## Run benchmark
+
+### Benchmark sglang
+```
+python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
+```
+
+```
+python3 bench_sglang.py --num-questions 200
+```
+
+
+### Benchmark vllm
+```
+python3 -m vllm.entrypoints.api_server --tokenizer-mode auto --model meta-llama/Llama-2-7b-chat-hf --disable-log-requests --port 21000
+```
+
+```
+python3 bench_other.py --num-questions 200 --backend vllm
+```
+
+
+### Benchmark lightllm
+```
+# A10G
+python -m lightllm.server.api_server --tokenizer_mode auto --model_dir ~/model_weights/llama-2-7b-chat-hf --max_total_token_num 16000 --port 22000
+```
+
+```
+python3 bench_other.py --num-questions 200 --backend lightllm
+```
+
+
+### Benchmark guidance
+```
+python3 bench_other.py --num-questions 200 --backend guidance --parallel 1 --n-ctx 4096 --model-path path/to/gguf
+```
+
+
+### Benchmark lmql
+```
+CUDA_VISIBLE_DEVICES=0,1 lmql serve-model meta-llama/Llama-2-7b-chat-hf --cuda --port 23000
+```
+
+```
+python3 bench_other.py --num-questions 100 --backend lmql --parallel 2
+```

benchmark/gsm8k/bench_other.py

+import argparse
+import ast
+import asyncio
+import json
+import re
+import time
+from concurrent.futures import ThreadPoolExecutor
+
+import numpy as np
+from tqdm import tqdm
+
+from sglang.test.test_utils import add_common_other_args_and_parse, get_call_generate
+from sglang.utils import download_and_cache_file, dump_state_text, read_jsonl
+
+INVALID = -9999999
+
+
+def get_one_example(lines, i, include_answer):
+    ret = "Question: " + lines[i]["question"] + "\nAnswer:"
+    if include_answer:
+        ret += " " + lines[i]["answer"]
+    return ret
+
+
+def get_few_shot_examples(lines, k):
+    ret = ""
+    for i in range(k):
+        ret += get_one_example(lines, i, True) + "\n\n"
+    return ret
+
+
+def get_answer_value(answer_str):
+    answer_str = answer_str.replace(",", "")
+    numbers = re.findall(r"\d+", answer_str)
+    if len(numbers) < 1:
+        return INVALID
+    try:
+        return ast.literal_eval(numbers[-1])
+    except SyntaxError:
+        return INVALID
+
+
+def main(args):
+    # Select backend
+    call_generate = get_call_generate(args)
+
+    # Read data
+    url = "https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl"
+    filename = download_and_cache_file(url)
+    lines = list(read_jsonl(filename))
+
+    # Construct prompts
+    num_questions = args.num_questions
+    num_shots = args.num_shots
+    few_shot_examples = get_few_shot_examples(lines, num_shots)
+
+    questions = []
+    labels = []
+    for i in range(len(lines[:num_questions])):
+        questions.append(get_one_example(lines, i, False))
+        labels.append(get_answer_value(lines[i]["answer"]))
+    assert all(l != INVALID for l in labels)
+
+    states = [None] * len(labels)
+
+    # Run requests
+    if args.backend != "lmql":
+        # Use thread pool
+        def get_one_answer(i):
+            answer = call_generate(
+                prompt=few_shot_examples + questions[i],
+                temperature=0,
+                max_tokens=256,
+                stop=["Question", "Assistant:", "<|separator|>"],
+            )
+            states[i] = answer
+
+        tic = time.perf_counter()
+        if args.parallel == 1:
+            for i in tqdm(range(len(questions))):
+                get_one_answer(i)
+        else:
+            with ThreadPoolExecutor(args.parallel) as executor:
+                list(
+                    tqdm(
+                        executor.map(get_one_answer, list(range(len(questions)))),
+                        total=len(questions),
+                    )
+                )
+
+    else:
+        # Use asyncio
+        async def batched_call(batch_size):
+            for i in range(0, len(questions), batch_size):
+                tasks = []
+                for q in questions[i : i + batch_size]:
+                    tasks.append(
+                        call_generate(
+                            few_shot_examples + q,
+                            temperature=0,
+                            max_tokens=256,
+                            stop="Question",
+                        )
+                    )
+                rets = await asyncio.gather(*tasks)
+                for j in range(len(rets)):
+                    states[i + j] = rets[j]
+
+        tic = time.perf_counter()
+        asyncio.run(batched_call(batch_size=args.parallel))
+    latency = time.perf_counter() - tic
+
+    preds = []
+    for i in range(len(states)):
+        preds.append(get_answer_value(states[i]))
+
+    # Compute accuracy
+    acc = np.mean(np.array(preds) == np.array(labels))
+    invalid = np.mean(np.array(preds) == INVALID)
+
+    # Print results
+    print(f"Accuracy: {acc:.3f}")
+    print(f"Invalid: {invalid:.3f}")
+    print(f"Latency: {latency:.3f} s")
+
+    # Dump results
+    dump_state_text(f"tmp_output_{args.backend}.txt", states)
+
+    with open(args.result_file, "a") as fout:
+        value = {
+            "task": "gsm8k",
+            "backend": args.backend,
+            "num_gpus": 1,
+            "latency": round(latency, 3),
+            "accuracy": round(acc, 3),
+            "num_requests": args.num_questions,
+            "other": {
+                "num_questions": args.num_questions,
+                "parallel": args.parallel,
+            },
+        }
+        fout.write(json.dumps(value) + "\n")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--num-shots", type=int, default=5)
+    parser.add_argument("--data-path", type=str, default="test.jsonl")
+    parser.add_argument("--num-questions", type=int, default=200)
+    args = add_common_other_args_and_parse(parser)
+    main(args)

benchmark/gsm8k/bench_sglang.py

+import argparse
+import ast
+import json
+import os
+import re
+import time
+
+import numpy as np
+
+from sglang.lang.api import set_default_backend
+from sglang.test.test_utils import (
+    add_common_sglang_args_and_parse,
+    dump_bench_raw_result,
+    select_sglang_backend,
+)
+from sglang.utils import download_and_cache_file, dump_state_text, read_jsonl
+
+INVALID = -9999999
+
+
+def get_one_example(lines, i, include_answer):
+    ret = "Question: " + lines[i]["question"] + "\nAnswer:"
+    if include_answer:
+        ret += " " + lines[i]["answer"]
+    return ret
+
+
+def get_few_shot_examples(lines, k):
+    ret = ""
+    for i in range(k):
+        ret += get_one_example(lines, i, True) + "\n\n"
+    return ret
+
+
+def get_answer_value(answer_str):
+    answer_str = answer_str.replace(",", "")
+    numbers = re.findall(r"\d+", answer_str)
+    if len(numbers) < 1:
+        return INVALID
+    try:
+        return ast.literal_eval(numbers[-1])
+    except SyntaxError:
+        return INVALID
+
+
+def main(args):
+    # Select backend
+    set_default_backend(select_sglang_backend(args))
+
+    # Read data
+    data_path = args.data_path
+    url = "https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl"
+    if not os.path.isfile(data_path):
+        data_path = download_and_cache_file(url)
+    lines = list(read_jsonl(data_path))
+
+    # Construct prompts
+    num_questions = args.num_questions
+    num_shots = args.num_shots
+    few_shot_examples = get_few_shot_examples(lines, num_shots)
+
+    questions = []
+    labels = []
+    for i in range(len(lines[:num_questions])):
+        questions.append(get_one_example(lines, i, False))
+        labels.append(get_answer_value(lines[i]["answer"]))
+    assert all(l != INVALID for l in labels)
+    arguments = [{"question": q} for q in questions]
+
+    #####################################
+    ######### SGL Program Begin #########
+    #####################################
+
+    import sglang as sgl
+
+    @sgl.function
+    def few_shot_gsm8k(s, question):
+        s += few_shot_examples + question
+        s += sgl.gen(
+            "answer", max_tokens=512, stop=["Question", "Assistant:", "<|separator|>"]
+        )
+
+    #####################################
+    ########## SGL Program End ##########
+    #####################################
+
+    # Run requests
+    tic = time.perf_counter()
+    states = few_shot_gsm8k.run_batch(
+        arguments,
+        temperature=0,
+        num_threads=args.parallel,
+        progress_bar=True,
+    )
+    latency = time.perf_counter() - tic
+
+    preds = []
+    for i in range(len(states)):
+        preds.append(get_answer_value(states[i]["answer"]))
+
+    # Compute accuracy
+    acc = np.mean(np.array(preds) == np.array(labels))
+    invalid = np.mean(np.array(preds) == INVALID)
+
+    # Compute speed
+    num_output_tokens = sum(
+        s.get_meta_info("answer")["completion_tokens"] for s in states
+    )
+    output_throughput = num_output_tokens / latency
+
+    # Print results
+    print(f"Accuracy: {acc:.3f}")
+    print(f"Invalid: {invalid:.3f}")
+    print(f"Latency: {latency:.3f} s")
+    print(f"Output throughput: {output_throughput:.3f} token/s")
+
+    # Dump results
+    dump_state_text(f"tmp_output_{args.backend}.txt", states)
+    dump_bench_raw_result(
+        path=args.raw_result_file,
+        states=states,
+        preds=preds,
+        labels=labels,
+    )
+
+    with open(args.result_file, "a") as fout:
+        value = {
+            "task": "gsm8k",
+            "backend": args.backend,
+            "num_gpus": 1,
+            "latency": round(latency, 3),
+            "accuracy": round(acc, 3),
+            "num_requests": args.num_questions,
+            "other": {
+                "num_questions": args.num_questions,
+                "parallel": args.parallel,
+            },
+        }
+        fout.write(json.dumps(value) + "\n")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--num-shots", type=int, default=5)
+    parser.add_argument("--data-path", type=str, default="test.jsonl")
+    parser.add_argument("--num-questions", type=int, default=200)
+    args = add_common_sglang_args_and_parse(parser)
+    main(args)

benchmark/hellaswag/README.md

+## Run benchmark
+
+### Benchmark sglang
+```
+python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
+```
+
+```
+python3 bench_sglang.py --num-questions 200
+```
+
+
+### Benchmark vllm
+```
+python3 -m vllm.entrypoints.api_server --tokenizer-mode auto --model meta-llama/Llama-2-7b-chat-hf --disable-log-requests --port 21000
+```
+
+```
+python3 bench_other.py --num-questions 200 --backend vllm
+```
+
+
+### Benchmark lightllm
+```
+# A10G
+python -m lightllm.server.api_server --tokenizer_mode auto --model_dir ~/model_weights/llama-2-7b-chat-hf --max_total_token_num 16000 --port 22000
+```
+
+```
+python3 bench_other.py --num-questions 200 --backend lightllm
+```
+
+
+### Benchmark guidance
+```
+CUDA_VISIBLE_DEVICES=0,1 python3 bench_other.py --num-questions 200 --backend guidance --parallel 1 --n-ctx 4096 --model-path path/to/gguf
+```
+
+
+### Benchmark lmql
+```
+lmql serve-model meta-llama/Llama-2-7b-chat-hf --cuda --port 23000
+```
+
+```
+python3 bench_other.py --num-questions 200 --backend lmql --port 23000 --parallel 1
+```

benchmark/hellaswag/bench_other.py

+import argparse
+import asyncio
+import json
+import time
+from concurrent.futures import ThreadPoolExecutor
+
+import numpy as np
+from tqdm import tqdm
+
+from sglang.test.test_utils import add_common_other_args_and_parse, get_call_select
+from sglang.utils import download_and_cache_file, read_jsonl
+
+
+def get_one_example(lines, i, include_answer):
+    ret = lines[i]["activity_label"] + ": " + lines[i]["ctx"] + " "
+    if include_answer:
+        ret += lines[i]["endings"][lines[i]["label"]]
+    return ret
+
+
+def get_few_shot_examples(lines, k):
+    ret = ""
+    for i in range(k):
+        ret += get_one_example(lines, i, True) + "\n\n"
+    return ret
+
+
+def main(args):
+    # Select backend
+    call_select = get_call_select(args)
+
+    # Read data
+    url = "https://raw.githubusercontent.com/rowanz/hellaswag/master/data/hellaswag_val.jsonl"
+    filename = download_and_cache_file(url)
+    lines = list(read_jsonl(filename))
+
+    # Construct prompts
+    num_questions = args.num_questions
+    num_shots = args.num_shots
+    few_shot_examples = get_few_shot_examples(lines, num_shots)
+
+    questions = []
+    choices = []
+    labels = []
+    for i in range(len(lines[:num_questions])):
+        questions.append(get_one_example(lines, i, False))
+        choices.append(lines[i]["endings"])
+        labels.append(lines[i]["label"])
+
+    preds = [None] * len(labels)
+
+    # Run requests
+    if args.backend != "lmql":
+        # Use thread pool
+        def get_one_answer(i):
+            preds[i] = call_select(
+                context=few_shot_examples + questions[i], choices=choices[i]
+            )
+
+        tic = time.perf_counter()
+        if args.parallel == 1:
+            for i in tqdm(range(len(questions))):
+                get_one_answer(i)
+        else:
+            with ThreadPoolExecutor(args.parallel) as executor:
+                list(
+                    tqdm(
+                        executor.map(get_one_answer, list(range(len(questions)))),
+                        total=len(questions),
+                    )
+                )
+    else:
+        # Use asyncio
+        async def batched_call(batch_size):
+            for i in range(0, len(questions), batch_size):
+                tasks = []
+                for q, c in zip(
+                    questions[i : i + batch_size], choices[i : i + batch_size]
+                ):
+                    tasks.append(call_select(context=few_shot_examples + q, choices=c))
+                rets = await asyncio.gather(*tasks)
+                for j in range(len(rets)):
+                    preds[i + j] = rets[j]
+
+        tic = time.perf_counter()
+        asyncio.run(batched_call(batch_size=args.parallel))
+
+    latency = time.perf_counter() - tic
+
+    # Compute accuracy
+    acc = np.mean(np.array(preds) == np.array(labels))
+    print(f"Latency: {latency:.3f}")
+    print(f"Accuracy: {acc:.3f}")
+
+    # Write results
+    with open(args.result_file, "a") as fout:
+        value = {
+            "task": "hellaswag",
+            "backend": args.backend,
+            "num_gpus": 1,
+            "latency": round(latency, 3),
+            "accuracy": round(acc, 3),
+            "num_requests": args.num_questions,
+            "other": {
+                "num_questions": args.num_questions,
+                "parallel": args.parallel,
+            },
+        }
+        fout.write(json.dumps(value) + "\n")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--num-shots", type=int, default=20)
+    parser.add_argument("--data-path", type=str, default="hellaswag_val.jsonl")
+    parser.add_argument("--num-questions", type=int, default=200)
+    args = add_common_other_args_and_parse(parser)
+    main(args)

benchmark/hellaswag/bench_sglang.py

+import argparse
+import json
+import os
+import time
+
+import numpy as np
+
+from sglang.lang.api import set_default_backend
+from sglang.test.test_utils import (
+    add_common_sglang_args_and_parse,
+    select_sglang_backend,
+)
+from sglang.utils import download_and_cache_file, read_jsonl
+
+
+def get_one_example(lines, i, include_answer):
+    ret = lines[i]["activity_label"] + ": " + lines[i]["ctx"] + " "
+    if include_answer:
+        ret += lines[i]["endings"][lines[i]["label"]]
+    return ret
+
+
+def get_few_shot_examples(lines, k):
+    ret = ""
+    for i in range(k):
+        ret += get_one_example(lines, i, True) + "\n\n"
+    return ret
+
+
+def main(args):
+    # Select backend
+    set_default_backend(select_sglang_backend(args))
+
+    # Read data
+    data_path = args.data_path
+    url = "https://raw.githubusercontent.com/rowanz/hellaswag/master/data/hellaswag_val.jsonl"
+    if not os.path.isfile(data_path):
+        data_path = download_and_cache_file(url)
+    lines = list(read_jsonl(data_path))
+
+    # Construct prompts
+    num_questions = args.num_questions
+    num_shots = args.num_shots
+    few_shot_examples = get_few_shot_examples(lines, num_shots)
+
+    questions = []
+    choices = []
+    labels = []
+    for i in range(len(lines[:num_questions])):
+        questions.append(get_one_example(lines, i, False))
+        choices.append(lines[i]["endings"])
+        labels.append(lines[i]["label"])
+    arguments = [{"question": q, "choices": c} for q, c in zip(questions, choices)]
+
+    #####################################
+    ######### SGL Program Begin #########
+    #####################################
+
+    import sglang as sgl
+
+    @sgl.function
+    def few_shot_hellaswag(s, question, choices):
+        s += few_shot_examples + question
+        s += sgl.select("answer", choices=choices)
+
+    #####################################
+    ########## SGL Program End ##########
+    #####################################
+
+    # Run requests
+    tic = time.perf_counter()
+    rets = few_shot_hellaswag.run_batch(
+        arguments,
+        temperature=0,
+        num_threads=args.parallel,
+        progress_bar=True,
+    )
+    preds = [choices[i].index(rets[i]["answer"]) for i in range(len(rets))]
+    latency = time.perf_counter() - tic
+
+    # Compute accuracy
+    acc = np.mean(np.array(preds) == np.array(labels))
+    print(f"Latency: {latency:.3f}")
+    print(f"Accuracy: {acc:.3f}")
+
+    # Write results
+    with open(args.result_file, "a") as fout:
+        value = {
+            "task": "hellaswag",
+            "backend": args.backend,
+            "num_gpus": 1,
+            "latency": round(latency, 3),
+            "accuracy": round(acc, 3),
+            "num_requests": args.num_questions,
+            "other": {
+                "num_questions": args.num_questions,
+                "parallel": args.parallel,
+            },
+        }
+        fout.write(json.dumps(value) + "\n")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--num-shots", type=int, default=20)
+    parser.add_argument("--data-path", type=str, default="hellaswag_val.jsonl")
+    parser.add_argument("--num-questions", type=int, default=200)
+    args = add_common_sglang_args_and_parse(parser)
+    main(args)

benchmark/hf3fs/bench.sh

+export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib/python3.12/dist-packages:/usr/local/lib/python3.12/dist-packages/torch/lib
+python3 benchmark/hf3fs/bench_client.py
+
+export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib/python3.12/dist-packages:/usr/local/lib/python3.12/dist-packages/torch/lib
+SGLANG_HICACHE_HF3FS_CONFIG_PATH=/sgl-workspace/sglang/benchmark/hf3fs/hf3fs.json \
+python3 benchmark/hf3fs/bench_storage.py
+
+export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib/python3.12/dist-packages:/usr/local/lib/python3.12/dist-packages/torch/lib
+export SGLANG_HICACHE_HF3FS_CONFIG_PATH=/sgl-workspace/sglang/benchmark/hf3fs/hf3fs.json
+echo '{"file_path_prefix": "/data/hf3fs-test-0", "file_size": 1099511627776, "numjobs": 16, "entries": 8}' > \
+${SGLANG_HICACHE_HF3FS_CONFIG_PATH}
+python3 benchmark/hf3fs/bench_zerocopy.py
+
+####################################################################################################
+
+rm -rf nohup.out && \
+nohup python3 -m sglang.launch_server \
+    --model-path /code/models/Qwen3-32B/ \
+    --host 0.0.0.0 --port 33301 \
+    --page-size 64 \
+    --enable-hierarchical-cache \
+    --hicache-ratio 2 --hicache-size 0 \
+    --hicache-write-policy write_through \
+    --hicache-storage-backend hf3fs &
+
+rm -rf bench_multiturn.out && \
+nohup python3 benchmark/hicache/bench_multiturn.py \
+    --model-path /code/models/Qwen3-32B \
+    --dataset-path /code/models/ShareGPT_V3_unfiltered_cleaned_split.json \
+    --port 33301 \
+    --request-length 2048 --num-clients 512 --num-rounds 3 --max-parallel 8 \
+    > bench_multiturn.out &
+
+####################################################################################################
+
+rm -rf nohup.out && \
+nohup python3 -m sglang.launch_server \
+    --model-path /code/models/DeepSeek-R1/ \
+    --tp 16 --nnodes 2 --node-rank 0 \
+    --dist-init-addr 10.74.249.153:5000 \
+    --host 0.0.0.0 --port 33301 \
+    --page-size 64 \
+    --enable-hierarchical-cache \
+    --hicache-ratio 2 --hicache-size 60 \
+    --hicache-write-policy write_through \
+    --hicache-storage-backend hf3fs &
+
+rm -rf bench_multiturn.out && \
+nohup python3 benchmark/hicache/bench_multiturn.py \
+    --model-path /code/models/Qwen3-32B \
+    --dataset-path /code/models/ShareGPT_V3_unfiltered_cleaned_split.json \
+    --port 33301 \
+    --request-length 2048 --num-clients 1024 --num-rounds 3 --max-parallel 8 \
+    > bench_multiturn.out &
+
+####################################################################################################
+
+ps aux | grep "sglang.launch_server" | grep -v grep | awk '{print $2}' | xargs kill -9
+ps aux | grep "bench_multiturn.py" | grep -v grep | awk '{print $2}' | xargs kill -9