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 lines
2.1 KiB
JSON
62 lines
2.1 KiB
JSON
{
|
|
"sglang": {
|
|
"llama": {
|
|
"gemm|nvjet": "gemm",
|
|
"fused_moe_kernel|GroupProblemShape|group_gemm_starts|bmm_|GemmUniversal": "moe_gemm",
|
|
"moe|sigmoid": "moe",
|
|
"CatArrayBatched|prepare_inputs": "prepare_next",
|
|
"ncclDevKernel|cross_device_reduce": "nccl_and_custom_ar",
|
|
"_norm_|Norm": "norm",
|
|
"topk": "topk",
|
|
"act_and_mul_": "activation",
|
|
"Rotary": "rope",
|
|
"SoftMax": "softmax",
|
|
"flash|fmha": "attn",
|
|
"elementwise": "elementwise",
|
|
"fp8_quant|cvt_|quantize": "quantize",
|
|
"reduce_kernel": "reduce",
|
|
"triton": "triton_kernel",
|
|
"CUDA mem": "non-gpu-H_D_memops",
|
|
".*": "misc"
|
|
},
|
|
"ds": {
|
|
"block_fp8_matmul": "block_fp8_gemm",
|
|
"gemm|matmul|nvjet": "gemm",
|
|
"fused_moe_kernel": "moe_gemm",
|
|
"moe|expert|sigmoid": "moe",
|
|
"CatArrayBatched|write_req_to": "prepare_next",
|
|
"ncclDevKernel|cross_device_reduce|all_gather": "nccl_and_custom_ar",
|
|
"Norm": "norm",
|
|
"topk": "topk",
|
|
"activation|act_and_mul": "activation",
|
|
"compute_position_kernel": "rope",
|
|
"elementwise": "elementwise",
|
|
"fp8_quant|quant_fp8|quantize": "quantize",
|
|
"SoftMax": "softmax",
|
|
"reduce": "reduce",
|
|
"_fwd_|create_flash|::mla::|KVCache": "attn",
|
|
"CUDA mem": "non-gpu-H_D_memops",
|
|
".*": "misc"
|
|
},
|
|
"gpt-oss": {
|
|
"gemm|nvjet": "gemm",
|
|
"fused_moe_kernel|_group_gemm|GroupProblemShape|GemmUniversal|bmm_|matmul_ogs_|_topk_forward|_combined_routing|_sum_bitmatrix_rows|_compute_writeback_idx": "moe_gemm",
|
|
"moe|sigmoid": "moe",
|
|
"CatArrayBatched|prepare_inputs": "prepare_next",
|
|
"_norm_|Norm": "norm",
|
|
"ncclDevKernel|cross_device_reduce|allreduce": "nccl_and_custom_ar",
|
|
"topk|TopK": "topk",
|
|
"act_and_mul_": "activation",
|
|
"Rotary": "rope",
|
|
"SoftMax": "softmax",
|
|
"flash|fmha": "attn",
|
|
"elementwise": "elementwise",
|
|
"fp8_quant|cvt_|quantize": "quantize",
|
|
"reduce_kernel": "reduce",
|
|
"triton": "triton_kernel",
|
|
"CUDA mem": "non-gpu-H_D_memops",
|
|
".*": "misc"
|
|
}
|
|
}
|
|
}
|