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

75 lines
2.5 KiB
Python

from __future__ import annotations
import logging
from typing import Callable, Dict, Type
import torch
from sglang.srt.kv_canary.buffer_group import CanaryBufferGroup
from sglang.srt.kv_canary.config import CanaryConfig
from sglang.srt.kv_canary.pool_patcher.adapters.dsv4 import attach_dsv4
from sglang.srt.kv_canary.pool_patcher.adapters.mha import attach_mha
from sglang.srt.kv_canary.pool_patcher.adapters.swa import attach_swa
from sglang.srt.kv_canary.pool_patcher.buffer_alloc import resolve_real_kv_read_bytes
from sglang.srt.mem_cache.deepseek_v4_memory_pool import DeepSeekV4TokenToKVPool
from sglang.srt.mem_cache.memory_pool import (
KVCache,
MHATokenToKVPool,
MHATokenToKVPoolFP4,
)
from sglang.srt.mem_cache.swa_memory_pool import SWAKVPool
logger = logging.getLogger(__name__)
PoolAttacher = Callable[..., tuple[CanaryBufferGroup, ...]]
_POOL_ATTACHERS: Dict[Type, PoolAttacher] = {
MHATokenToKVPool: attach_mha,
MHATokenToKVPoolFP4: attach_mha,
SWAKVPool: attach_swa,
DeepSeekV4TokenToKVPool: attach_dsv4,
}
def register_pool_attacher(pool_class: Type, attacher: PoolAttacher) -> None:
_POOL_ATTACHERS[pool_class] = attacher
def attach_canary_buffers(
*,
pool: KVCache,
config: CanaryConfig,
device: torch.device,
kv_token_id_vs_position_offset: int,
) -> tuple[CanaryBufferGroup, ...]:
"""Install canary buffers on a KV pool and return the resulting CanaryBufferGroup tuple.
``kv_token_id_vs_position_offset`` is propagated into every produced :class:`CanaryBufferGroup` (0 for target
pools; 1 for draft pools where the input-ids rotation shifts the slot-to-token mapping by one).
"""
attacher = _POOL_ATTACHERS.get(type(pool))
if attacher is None:
raise NotImplementedError(
f"kv-canary: no attacher registered for pool class {type(pool).__name__}; "
f"supported: {sorted(cls.__name__ for cls in _POOL_ATTACHERS)}"
)
read_bytes = resolve_real_kv_read_bytes(config)
groups = attacher(
pool=pool,
device=device,
read_bytes=read_bytes,
kv_token_id_vs_position_offset=kv_token_id_vs_position_offset,
)
logger.info(
"attach_canary_buffers: pool=%s attacher=%s read_bytes=%d n_groups=%d kinds=%s "
"kv_token_id_vs_position_offset=%d",
type(pool).__name__,
attacher.__name__,
read_bytes,
len(groups),
[g.kind.name for g in groups],
kv_token_id_vs_position_offset,
)
return groups