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
64 lines
1.8 KiB
Python
64 lines
1.8 KiB
Python
from .attn import (
|
|
fused_store_cache,
|
|
get_paged_mqa_logits_metadata,
|
|
triton_create_paged_compress_data,
|
|
)
|
|
from .c128_cleanup import clear_unaccepted_c128_draft_states
|
|
from .compress import (
|
|
CompressorDecodePlan,
|
|
CompressorPrefillPlan,
|
|
compress_forward,
|
|
compress_norm_rope_store,
|
|
)
|
|
from .compress_old import fused_norm_rope_inplace
|
|
from .elementwise import (
|
|
fused_k_norm_rope_flashmla,
|
|
fused_q_indexer_rope_first_quant,
|
|
fused_q_indexer_rope_hadamard_fp4_quant,
|
|
fused_q_indexer_rope_hadamard_quant,
|
|
fused_q_norm_rope,
|
|
fused_rope_inplace,
|
|
)
|
|
from .fp8_wo_a import sglang_per_token_group_quant_fp8_dsv4_wo_a
|
|
from .gemm import linear_bf16_fp32
|
|
from .moe import (
|
|
hash_topk,
|
|
mask_topk_ids,
|
|
mega_moe_pre_dispatch,
|
|
silu_and_mul_clamp,
|
|
silu_and_mul_contig_post_quant,
|
|
silu_and_mul_masked_post_quant,
|
|
)
|
|
from .topk import plan_topk_v2, topk_transform_512, topk_transform_512_v2
|
|
from .utils import make_name
|
|
|
|
__all__ = [
|
|
"CompressorDecodePlan",
|
|
"CompressorPrefillPlan",
|
|
"compress_forward",
|
|
"compress_norm_rope_store",
|
|
"clear_unaccepted_c128_draft_states",
|
|
"fused_norm_rope_inplace",
|
|
"fused_store_cache",
|
|
"fused_rope_inplace",
|
|
"fused_q_norm_rope",
|
|
"fused_q_indexer_rope_first_quant",
|
|
"fused_q_indexer_rope_hadamard_fp4_quant",
|
|
"fused_q_indexer_rope_hadamard_quant",
|
|
"fused_k_norm_rope_flashmla",
|
|
"sglang_per_token_group_quant_fp8_dsv4_wo_a",
|
|
"make_name",
|
|
"linear_bf16_fp32",
|
|
"get_paged_mqa_logits_metadata",
|
|
"triton_create_paged_compress_data",
|
|
"topk_transform_512",
|
|
"topk_transform_512_v2",
|
|
"plan_topk_v2",
|
|
"hash_topk",
|
|
"mega_moe_pre_dispatch",
|
|
"mask_topk_ids",
|
|
"silu_and_mul_clamp",
|
|
"silu_and_mul_masked_post_quant",
|
|
"silu_and_mul_contig_post_quant",
|
|
]
|