sgl-project--sglang
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
84 行
2.7 KiB
Python
84 行
2.7 KiB
Python
import sys
|
|
|
|
import pytest
|
|
import torch
|
|
|
|
from sglang.test.ci.ci_register import register_cpu_ci
|
|
|
|
register_cpu_ci(est_time=25, suite="base-b-test-cpu")
|
|
|
|
torch.manual_seed(42)
|
|
|
|
DEVICE = "cpu"
|
|
CACHE_SIZE = 4096
|
|
|
|
# for fp8 KV stored as uint8, e.g. float8_e4m3fn and float8_e5m2
|
|
DTYPES = [torch.float16, torch.bfloat16, torch.uint8]
|
|
DTYPE_IDS = ["float16", "bfloat16", "uint8"]
|
|
|
|
|
|
def _store_cache_cpu(k, v, k_cache, v_cache, indices):
|
|
row_dim = k.size(1) * k.size(2)
|
|
torch.ops.sgl_kernel.store_cache_cpu(k, v, k_cache, v_cache, indices, row_dim)
|
|
|
|
|
|
def _random_tensor(shape, dtype):
|
|
"""FP8 KV is stored as uint8; randn is not implemented for Byte."""
|
|
if dtype == torch.uint8:
|
|
return torch.randint(0, 256, shape, dtype=torch.uint8, device=DEVICE)
|
|
return torch.randn(shape, dtype=dtype, device=DEVICE)
|
|
|
|
|
|
@pytest.mark.parametrize("dtype", DTYPES, ids=DTYPE_IDS)
|
|
@pytest.mark.parametrize("head_dim", [64, 128])
|
|
@pytest.mark.parametrize("num_heads", [1, 8, 16, 32])
|
|
@pytest.mark.parametrize("batch_size", [1, 7, 133])
|
|
def test_store_cache(batch_size, num_heads, head_dim, dtype):
|
|
shape = (batch_size, num_heads, head_dim)
|
|
cache_shape = (CACHE_SIZE, num_heads, head_dim)
|
|
k = _random_tensor(shape, dtype)
|
|
v = _random_tensor(shape, dtype)
|
|
k_cache = _random_tensor(cache_shape, dtype)
|
|
v_cache = _random_tensor(cache_shape, dtype)
|
|
indices = torch.randperm(CACHE_SIZE, device=DEVICE, dtype=torch.int64)[:batch_size]
|
|
|
|
k_cache_ref = k_cache.clone()
|
|
v_cache_ref = v_cache.clone()
|
|
k_cache_ref[indices] = k
|
|
v_cache_ref[indices] = v
|
|
|
|
_store_cache_cpu(k, v, k_cache, v_cache, indices)
|
|
|
|
assert torch.equal(k_cache, k_cache_ref)
|
|
assert torch.equal(v_cache, v_cache_ref)
|
|
|
|
|
|
@pytest.mark.parametrize("dtype", DTYPES, ids=DTYPE_IDS)
|
|
@pytest.mark.parametrize("head_dim", [64, 128])
|
|
@pytest.mark.parametrize("num_heads", [1, 8])
|
|
@pytest.mark.parametrize("batch_size", [11])
|
|
def test_store_cache_int32_indices(batch_size, num_heads, head_dim, dtype):
|
|
shape = (batch_size, num_heads, head_dim)
|
|
cache_shape = (CACHE_SIZE, num_heads, head_dim)
|
|
k = _random_tensor(shape, dtype)
|
|
v = _random_tensor(shape, dtype)
|
|
k_cache = _random_tensor(cache_shape, dtype)
|
|
v_cache = _random_tensor(cache_shape, dtype)
|
|
indices = torch.randperm(CACHE_SIZE, device=DEVICE, dtype=torch.int64)[
|
|
:batch_size
|
|
].to(torch.int32)
|
|
|
|
k_cache_ref = k_cache.clone()
|
|
v_cache_ref = v_cache.clone()
|
|
k_cache_ref[indices.long()] = k
|
|
v_cache_ref[indices.long()] = v
|
|
|
|
_store_cache_cpu(k, v, k_cache, v_cache, indices)
|
|
|
|
assert torch.equal(k_cache, k_cache_ref)
|
|
assert torch.equal(v_cache, v_cache_ref)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(pytest.main([__file__]))
|