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
2.6 KiB
Python
94 lines
2.6 KiB
Python
import argparse
|
|
import json
|
|
import time
|
|
|
|
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
|
|
|
|
|
|
@sgl.function
|
|
def multi_document_qa(s, docs, question):
|
|
s += sgl.user_begin()
|
|
s += "Please answer a question according to given documents.\n"
|
|
s += "Question:" + question + "Documents begin.\n"
|
|
|
|
forks = s.fork(len(docs))
|
|
forks += lambda i: docs[i]
|
|
forks.join("concate_and_append")
|
|
|
|
s += "\nDocuments end."
|
|
s += (
|
|
"\n\nBased on the above documents, please answer this question:\n"
|
|
+ question
|
|
+ "\nAnswer in three words or fewer."
|
|
)
|
|
s += sgl.user_end()
|
|
s += sgl.assistant(sgl.gen("answer", max_tokens=16))
|
|
|
|
|
|
def main(args):
|
|
lines = read_jsonl(args.data_path)
|
|
l = lines[0]
|
|
arguments = []
|
|
labels = []
|
|
for i in range(len(l["questions"][: args.num_questions])):
|
|
arguments.append(
|
|
{
|
|
"docs": l["documents"][:10],
|
|
"question": l["questions"][i],
|
|
}
|
|
)
|
|
labels.append(l["answers"][i])
|
|
|
|
# Select backend
|
|
backend = select_sglang_backend(args)
|
|
sgl.set_default_backend(backend)
|
|
|
|
# Run requests
|
|
tic = time.perf_counter()
|
|
states = multi_document_qa.run_batch(
|
|
arguments, temperature=0, num_threads=args.parallel, progress_bar=True
|
|
)
|
|
latency = time.perf_counter() - tic
|
|
|
|
# Compute accuracy
|
|
print([s["answer"] for s in states])
|
|
correct = 0
|
|
for s, label in zip(states, labels):
|
|
answer = s["answer"].lower()
|
|
if all(x in answer for x in label.lower().split(" ")):
|
|
correct += 1
|
|
accuracy = correct / len(labels)
|
|
print(f"Accuracy: {accuracy:.3f}")
|
|
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": "multi_document_qa",
|
|
"backend": args.backend,
|
|
"num_gpus": 1,
|
|
"latency": round(latency, 3),
|
|
"num_requests": args.num_questions,
|
|
"accuracy": accuracy,
|
|
"other": {
|
|
"num_questions": args.num_questions,
|
|
"parallel": args.parallel,
|
|
},
|
|
}
|
|
fout.write(json.dumps(value) + "\n")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--data-path", type=str, default="questions.jsonl")
|
|
parser.add_argument("--num-questions", type=int, default=100)
|
|
args = add_common_sglang_args_and_parse(parser)
|
|
main(args)
|