94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
94 lines
2.7 KiB
Python
94 lines
2.7 KiB
Python
import json
|
|
import time
|
|
from argparse import ArgumentParser
|
|
from concurrent.futures import ThreadPoolExecutor
|
|
from functools import partial
|
|
|
|
from data_gen import gen_arguments
|
|
from tqdm import tqdm
|
|
from vllm.transformers_utils.tokenizer import get_tokenizer
|
|
|
|
from sglang.test.test_utils import add_common_other_args_and_parse, get_call_generate
|
|
from sglang.utils import dump_state_text
|
|
|
|
|
|
def multi_turns(generate, qas):
|
|
s = ""
|
|
for qa in qas:
|
|
s += qa["prompt"]
|
|
s += generate(s, max_tokens=qa["new_tokens"])
|
|
|
|
return s
|
|
|
|
|
|
def main(args):
|
|
print(args)
|
|
|
|
tokenizer = get_tokenizer(args.tokenizer, trust_remote_code=args.trust_remote_code)
|
|
|
|
multi_qas = gen_arguments(args, tokenizer)
|
|
|
|
states = [None] * args.num_qa
|
|
|
|
call_generate = partial(get_call_generate(args), temperature=0)
|
|
|
|
def get_one_answer(i):
|
|
states[i] = multi_turns(generate=call_generate, **multi_qas[i])
|
|
|
|
tic = time.perf_counter()
|
|
if args.parallel == 1:
|
|
for i in tqdm(range(len(multi_qas))):
|
|
get_one_answer(i)
|
|
else:
|
|
with ThreadPoolExecutor(args.parallel) as executor:
|
|
rets = list(
|
|
tqdm(
|
|
executor.map(get_one_answer, list(range(len(multi_qas)))),
|
|
total=len(multi_qas),
|
|
)
|
|
)
|
|
for _ in rets:
|
|
pass
|
|
|
|
latency = time.perf_counter() - tic
|
|
|
|
# Compute accuracy
|
|
print(f"Latency: {latency:.3f}")
|
|
|
|
dump_state_text(f"tmp_output_{args.backend}.txt", states)
|
|
|
|
with open(args.result_file, "a") as fout:
|
|
value = {
|
|
"task": "multi_turn_chat",
|
|
"backend": args.backend,
|
|
"num_gpus": 1,
|
|
"latency": round(latency, 3),
|
|
"num_requests": args.num_qa,
|
|
"num_turns": args.turns,
|
|
"other": {
|
|
"parallel": args.parallel,
|
|
"output_mode": "long" if args.long else "short",
|
|
},
|
|
}
|
|
fout.write(json.dumps(value) + "\n")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
parser = ArgumentParser()
|
|
parser.add_argument("--turns", type=int, default=4)
|
|
parser.add_argument("--num-qa", type=int, default=20)
|
|
parser.add_argument("--min-len-q", type=int, default=256)
|
|
parser.add_argument("--max-len-q", type=int, default=512)
|
|
parser.add_argument("--min-len-a", type=int, default=4)
|
|
parser.add_argument("--max-len-a", type=int, default=8)
|
|
parser.add_argument("--tokenizer", type=str, required=True)
|
|
parser.add_argument("--trust-remote-code", action="store_true")
|
|
parser.add_argument("--long", action="store_true")
|
|
args = add_common_other_args_and_parse(parser)
|
|
|
|
if args.long:
|
|
args.min_len_a = 256
|
|
args.max_len_a = 512
|
|
args.num_qa = 20
|
|
main(args)
|