sgl-project--sglang
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
119 行
4.0 KiB
Python
119 行
4.0 KiB
Python
"""Unit tests for tiktoken_tokenizer — no server, no model loading."""
|
|
|
|
import unittest
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
from sglang.test.ci.ci_register import register_cpu_ci
|
|
from sglang.test.test_utils import CustomTestCase
|
|
|
|
register_cpu_ci(est_time=7, suite="base-a-test-cpu")
|
|
|
|
from sglang.srt.tokenizer.tiktoken_tokenizer import (
|
|
CONTROL_TOKEN_TEXTS,
|
|
DEFAULT_CONTROL_TOKENS,
|
|
DEFAULT_SPECIAL_TOKENS,
|
|
EOS,
|
|
PAD,
|
|
RESERVED_TOKEN_TEXTS,
|
|
SEP,
|
|
TiktokenProcessor,
|
|
TiktokenTokenizer,
|
|
)
|
|
|
|
|
|
class TestConstants(CustomTestCase):
|
|
def test_reserved_token_count(self):
|
|
self.assertEqual(len(RESERVED_TOKEN_TEXTS), 125)
|
|
|
|
def test_reserved_token_format(self):
|
|
self.assertEqual(RESERVED_TOKEN_TEXTS[0], "<|reserved_3|>")
|
|
self.assertEqual(RESERVED_TOKEN_TEXTS[-1], "<|reserved_127|>")
|
|
|
|
def test_control_token_count(self):
|
|
self.assertEqual(len(CONTROL_TOKEN_TEXTS), 704)
|
|
|
|
def test_control_token_format(self):
|
|
self.assertEqual(CONTROL_TOKEN_TEXTS[0], "<|control1|>")
|
|
self.assertEqual(CONTROL_TOKEN_TEXTS[-1], "<|control704|>")
|
|
|
|
def test_default_special_tokens_contains_all(self):
|
|
self.assertIn(PAD, DEFAULT_SPECIAL_TOKENS)
|
|
self.assertIn(EOS, DEFAULT_SPECIAL_TOKENS)
|
|
self.assertIn(SEP, DEFAULT_SPECIAL_TOKENS)
|
|
|
|
def test_default_control_tokens_values(self):
|
|
# Note: "sep" maps to EOS and "eos" maps to SEP in the source code
|
|
self.assertEqual(DEFAULT_CONTROL_TOKENS["pad"], PAD)
|
|
self.assertEqual(DEFAULT_CONTROL_TOKENS["sep"], EOS)
|
|
self.assertEqual(DEFAULT_CONTROL_TOKENS["eos"], SEP)
|
|
|
|
|
|
class TestTiktokenProcessor(CustomTestCase):
|
|
def setUp(self):
|
|
tokenizer_patcher = patch(
|
|
"sglang.srt.tokenizer.tiktoken_tokenizer.TiktokenTokenizer"
|
|
)
|
|
tokenizer_patcher.start()
|
|
self.addCleanup(tokenizer_patcher.stop)
|
|
self.processor = TiktokenProcessor(name="dummy")
|
|
|
|
def test_image_processor_wraps_image_in_list(self):
|
|
image = "fake_image_data"
|
|
result = self.processor.image_processor(image)
|
|
self.assertEqual(result["pixel_values"], [image])
|
|
|
|
def test_image_processor_with_none(self):
|
|
result = self.processor.image_processor(None)
|
|
self.assertEqual(result["pixel_values"], [None])
|
|
|
|
|
|
class TestTiktokenTokenizer(CustomTestCase):
|
|
def setUp(self):
|
|
from jinja2 import Template
|
|
|
|
self.tok = TiktokenTokenizer.__new__(TiktokenTokenizer)
|
|
self.mock_tokenizer = MagicMock()
|
|
self.tok.tokenizer = self.mock_tokenizer
|
|
self.tok.chat_template = "dummy"
|
|
self.tok.chat_template_jinja = Template(
|
|
"{% for message in messages %}"
|
|
"{{ message['role'] }}: {{ message['content'] }}"
|
|
"{% endfor %}"
|
|
"{% if add_generation_prompt %}assistant:{% endif %}"
|
|
)
|
|
|
|
def test_batch_decode_flat_list_wraps_each(self):
|
|
self.mock_tokenizer.decode_batch.return_value = ["a", "b"]
|
|
self.tok.batch_decode([1, 2])
|
|
self.mock_tokenizer.decode_batch.assert_called_once_with([[1], [2]])
|
|
|
|
def test_call_returns_input_ids(self):
|
|
self.mock_tokenizer.encode.return_value = [1, 2, 3]
|
|
result = self.tok(["hello", "world"])
|
|
self.assertIn("input_ids", result)
|
|
self.assertEqual(len(result["input_ids"]), 2)
|
|
|
|
def test_apply_chat_template_no_tokenize(self):
|
|
messages = [{"role": "user", "content": "hello"}]
|
|
result = self.tok.apply_chat_template(
|
|
messages=messages,
|
|
tokenize=False,
|
|
add_generation_prompt=False,
|
|
)
|
|
self.assertIsInstance(result, str)
|
|
self.assertIn("hello", result)
|
|
|
|
def test_apply_chat_template_with_tokenize(self):
|
|
self.mock_tokenizer.encode.return_value = [1, 2, 3]
|
|
messages = [{"role": "user", "content": "hello"}]
|
|
result = self.tok.apply_chat_template(
|
|
messages=messages,
|
|
tokenize=True,
|
|
add_generation_prompt=False,
|
|
)
|
|
self.assertIsInstance(result, list)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|