Files
wehub-resource-sync 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
chore: import upstream snapshot with attribution
2026-07-13 12:38:16 +08:00

128 lines
4.4 KiB
Python

import logging
from sglang.srt.environ import envs
logger = logging.getLogger(__name__)
def patch_tokenizer(tokenizer):
if not envs.SGLANG_PATCH_TOKENIZER.get():
return tokenizer
if _is_kimi_tiktoken_tokenizer(tokenizer):
logger.info(
f"Applying special tokens cache patch for Kimi tokenizer: {type(tokenizer)}"
)
return _SpecialTokensCachePatcher.patch(tokenizer)
return tokenizer
def unpatch_tokenizer(tokenizer):
return _SpecialTokensCachePatcher.unpatch(tokenizer)
def _is_kimi_tiktoken_tokenizer(tokenizer):
cls = type(tokenizer)
class_name = cls.__name__
module_name = cls.__module__ or ""
return class_name == "TikTokenTokenizer" and "tokenization_kimi" in module_name
def decode_without_hf_kwargs(tokenizer, token_ids, skip_special_tokens):
if skip_special_tokens:
special_ids = getattr(tokenizer, "all_special_ids_set", None)
if special_ids is None:
special_ids = getattr(tokenizer, "all_special_ids", None)
if special_ids is not None:
special_ids_set = set(special_ids)
token_ids = [tid for tid in token_ids if tid not in special_ids_set]
return tokenizer.decode(token_ids)
class _SpecialTokensCachePatcher:
_PATCHED_FLAG = "_sglang_special_tokens_patched"
_CACHED_TOKENS_ATTR = "_sglang_cached_special_tokens"
_CACHED_IDS_ATTR = "_sglang_cached_special_ids"
@classmethod
def patch(cls, tokenizer):
tokenizer_cls = type(tokenizer)
if getattr(tokenizer_cls, cls._PATCHED_FLAG, False):
return tokenizer
tokenizer_cls._original_all_special_tokens = (
tokenizer_cls.all_special_tokens.fget
)
tokenizer_cls._original_all_special_ids = tokenizer_cls.all_special_ids.fget
tokenizer_cls._original_add_special_tokens = tokenizer_cls.add_special_tokens
tokenizer_cls._original_add_tokens = tokenizer_cls.add_tokens
patched_all_special_tokens = _make_cached_property(
cls._CACHED_TOKENS_ATTR, tokenizer_cls._original_all_special_tokens
)
patched_all_special_ids = _make_cached_property(
cls._CACHED_IDS_ATTR, tokenizer_cls._original_all_special_ids
)
def patched_add_special_tokens(self, *args, **kwargs):
assert (
False
), "Cannot modify special tokens after patch. Call unpatch_tokenizer first."
def patched_add_tokens(self, new_tokens, special_tokens=False):
assert (
not special_tokens
), "Cannot add special tokens after patch. Call unpatch_tokenizer first."
return tokenizer_cls._original_add_tokens(
self, new_tokens, special_tokens=False
)
tokenizer_cls.all_special_tokens = patched_all_special_tokens
tokenizer_cls.all_special_ids = patched_all_special_ids
tokenizer_cls.add_special_tokens = patched_add_special_tokens
tokenizer_cls.add_tokens = patched_add_tokens
setattr(tokenizer_cls, cls._PATCHED_FLAG, True)
return tokenizer
@classmethod
def unpatch(cls, tokenizer):
tokenizer_cls = type(tokenizer)
if not getattr(tokenizer_cls, cls._PATCHED_FLAG, False):
return tokenizer
tokenizer_cls.all_special_tokens = property(
tokenizer_cls._original_all_special_tokens
)
tokenizer_cls.all_special_ids = property(
tokenizer_cls._original_all_special_ids
)
tokenizer_cls.add_special_tokens = tokenizer_cls._original_add_special_tokens
tokenizer_cls.add_tokens = tokenizer_cls._original_add_tokens
del tokenizer_cls._original_all_special_tokens
del tokenizer_cls._original_all_special_ids
del tokenizer_cls._original_add_special_tokens
del tokenizer_cls._original_add_tokens
delattr(tokenizer_cls, cls._PATCHED_FLAG)
for attr in [cls._CACHED_TOKENS_ATTR, cls._CACHED_IDS_ATTR]:
if hasattr(tokenizer, attr):
delattr(tokenizer, attr)
logger.info(f"Unpatched special tokens cache for {tokenizer_cls.__name__}")
return tokenizer
def _make_cached_property(cache_attr, original_fn):
@property
def cached_prop(self):
if getattr(self, cache_attr, None) is None:
setattr(self, cache_attr, original_fn(self))
return getattr(self, cache_attr)
return cached_prop