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
62 行
2.0 KiB
Python
62 行
2.0 KiB
Python
"""Equivalence tests for the migrated InfLLM-V2 FlashAttention API.
|
|
|
|
These compare the ``sgl_kernel.infllm_v2`` implementations against the original
|
|
``infllm_v2`` package (3rdparty/infllmv2_cuda_impl). Both call the same CUDA
|
|
kernels, so outputs are expected to match closely. The whole module is skipped
|
|
if the reference ``infllm_v2`` package is not importable.
|
|
"""
|
|
|
|
import pytest
|
|
import torch
|
|
|
|
sgl = pytest.importorskip("sgl_kernel.infllm_v2")
|
|
ref = pytest.importorskip("infllm_v2")
|
|
|
|
pytestmark = pytest.mark.skipif(
|
|
not torch.cuda.is_available(), reason="CUDA is required for InfLLM-V2 kernels"
|
|
)
|
|
|
|
|
|
def _assert_close(a, b, name):
|
|
a = a.float()
|
|
b = b.float()
|
|
assert a.shape == b.shape, f"{name}: shape mismatch {a.shape} vs {b.shape}"
|
|
max_diff = (a - b).abs().max().item()
|
|
assert torch.allclose(a, b, atol=1e-2, rtol=1e-2), f"{name}: max diff {max_diff}"
|
|
|
|
|
|
@pytest.mark.parametrize("head_dim", [64, 128])
|
|
@pytest.mark.parametrize("causal", [False, True])
|
|
@pytest.mark.parametrize("seqlen_q,seqlen_k", [(256, 16), (64, 17)])
|
|
def test_stage1_matches_reference(head_dim, causal, seqlen_q, seqlen_k):
|
|
torch.manual_seed(0)
|
|
n_heads, n_kv_heads = 32, 2
|
|
dtype = torch.bfloat16
|
|
|
|
q = torch.randn(n_heads, seqlen_q, head_dim, dtype=dtype, device="cuda")
|
|
k = torch.randn(n_kv_heads, seqlen_k, head_dim, dtype=dtype, device="cuda")
|
|
|
|
cu_seqlens_q = torch.tensor([0, seqlen_q], dtype=torch.int32, device="cuda")
|
|
cu_seqlens_k = torch.tensor([0, seqlen_k], dtype=torch.int32, device="cuda")
|
|
|
|
q = q.transpose(0, 1).contiguous()
|
|
k = k.transpose(0, 1).contiguous()
|
|
|
|
common = dict(
|
|
cu_seqlens_q=cu_seqlens_q,
|
|
cu_seqlens_k=cu_seqlens_k,
|
|
cu_seqlens_v=cu_seqlens_k,
|
|
max_seqlen_q=seqlen_q,
|
|
max_seqlen_k=seqlen_k,
|
|
causal=causal,
|
|
)
|
|
out_ref = ref.infllmv2_attn_stage1(q, k, k, **common)
|
|
out_sgl = sgl.infllmv2_attn_stage1(q, k, k, **common)
|
|
_assert_close(out_sgl, out_ref, "stage1")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import sys
|
|
|
|
sys.exit(pytest.main([__file__, "-v"]))
|