sglang

ascend

[NPU]Add a full test pipeline on NPU, resolve issues in the NPU test architecture (#20751 )

2026-04-01 19:56:31 +08:00

attention

Support Qwen3 MoE context parallel (#18233 )

2026-03-22 01:27:20 -07:00

ci

[CI] Enable failfast (-f) by default in run_suite.py (#21330 )

2026-03-24 17:04:42 -07:00

external_models

Fix external_models import path and migrate model loading tests (#16458 )

2026-01-08 23:43:49 -08:00

kits

[Test] Consolidate eval accuracy test mixins into eval_accuracy_kit (#21047 )

2026-03-26 14:26:46 -07:00

longbench_v2

Feature/longbench v2 evaluation utils (#10949 )

2025-10-07 14:17:31 +08:00

server_fixtures

Fix RDMA device mapping for non-zero GPU indices in disaggregation tests (#21303 )

2026-03-24 22:56:57 -07:00

speculative

Support FlashAttention3 page_size > 1 and topk > 1 case with paged attn and spec decode (#7725 )

2025-11-26 11:44:41 +08:00

__init__.py

Fix circular imports in gptq.py and unblock test explorer (#4736 )

2025-03-24 18:07:08 -07:00

accuracy_test_runner.py

feat(ci): add GB300 nightly benchmark test suites (#21487 )

2026-03-28 21:54:03 -07:00

bench_one_batch_server_internal.py

Revert "fix: use consistent time denominator for throughput metrics in bench_one_batch_server" (#21276 )

2026-03-23 22:14:54 -07:00

doc_patch.py

[CI] fix: notebook ci often OOM (#20199 )

2026-03-09 22:32:41 -07:00

few_shot_gsm8k_engine.py

[Fix] Fix uvloop get_event_loop() is not suitable for 0.22.x (#13612 )

2025-11-25 01:20:00 +08:00

few_shot_gsm8k.py

[Misc] Normalize --host parameter to use plain hostname without scheme (#19309 )

2026-02-25 00:37:24 -08:00

get_logits_ut.py

Support DeepSeek V3.2 Exp (#11061 )

2025-10-06 00:24:15 -07:00

gpt_oss_common.py

[AMD] rocm 7.2 image release, PR test, Nightly Test (#17799 )

2026-02-11 21:29:25 -08:00

kl_test_utils.py

[Qwen3-next] support mamba radix cache for overlap scheduler (#14792 )

2025-12-14 18:54:16 -08:00

long_prompt.txt

minor: Add basic editorconfig and pre-commit hooks to enforce style for whitespaces (#1926 )

2024-11-06 13:46:04 +00:00

lora_utils.py

chore: bump flashinfer version to 0.6.7 (#21422 )

2026-03-31 21:18:16 -07:00

nightly_bench_utils.py

Upload nightly test metrics to GH artifacts (#17696 )

2026-01-25 14:35:14 -08:00

nightly_utils.py

ci: move metrics scripts under scripts/ci/utils (#20986 )

2026-03-19 23:47:57 -07:00

performance_test_runner.py

Enable SGLANG_ENABLE_SPEC_V2 for nightly speculative decoding tests (#18719 )

2026-02-14 23:00:33 +08:00

run_combined_tests.py

feat(ci): add GB300 nightly benchmark test suites (#21487 )

2026-03-28 21:54:03 -07:00

run_eval.py

Add latency and throughput metrics to run_eval (#21793 )

2026-03-31 18:36:14 -07:00

runners.py

Fix HFRunner hang when subprocess dies during init (#21582 )

2026-03-27 21:22:42 -07:00

send_one.py

Replace clamp_position with JIT kernel + platform dispatch (#20999 )

2026-03-21 21:26:26 -07:00

simple_eval_aime25.py

[Feature] Add AIME25 dataset support for SGLang simple_eval (#14990 )

2025-12-15 21:59:40 -08:00

simple_eval_common.py

[Misc] Add network timeout to eval dataset downloads (#21873 )

2026-04-01 13:16:14 -07:00

simple_eval_gpqa.py

[Misc] Add network timeout to eval dataset downloads (#21873 )

2026-04-01 13:16:14 -07:00

simple_eval_gsm8k.py

[eval] GSM8k support for run_eval (#17041 )

2026-01-16 11:10:17 +08:00

simple_eval_humaneval.py

Allow benchmarking tool to handle empty response (#12174 )

2025-10-29 20:26:23 -07:00

simple_eval_longbench_v2.py

[Fix] Improve longbench prompt and other logics (#11474 )

2025-10-12 15:04:28 -07:00

simple_eval_math.py

[Misc] Add network timeout to eval dataset downloads (#21873 )

2026-04-01 13:16:14 -07:00

simple_eval_mgsm.py

[Misc] Tiny: Add test network timeouts and dynamic max-parallel for 5090/2-gpu runners (#21800 )

2026-03-31 18:27:39 -07:00

simple_eval_mmlu.py

[Misc] Add network timeout to eval dataset downloads (#21873 )

2026-04-01 13:16:14 -07:00

simple_eval_mmmu_vlm.py

fix nightly vlm ci : restore original eval for requests without regex (#14875 )

2025-12-10 23:13:25 -08:00

test_activation.py

[AMD] Add silu_and_mul, gelu_and_mul, gelu_tanh_and_mul, and gelu_quick kernels for AMD GPUs (#7135 )

2025-07-24 23:44:28 -07:00

test_block_fp8_deep_gemm_blackwell.py

[1/2] Refactor DeepGeem requant for FP8 Linear on Blackwell (#13601 )

2025-11-23 16:07:56 -08:00

test_block_fp8.py

[WIP]enable mxfp8 on nvidia sm120 (#19112 )

2026-03-01 19:06:43 -08:00

test_custom_ops.py

docs: improve CI and testing documentation (#21202 )

2026-03-23 10:48:50 -07:00

test_cutlass_moe.py

[sgl-kernel][5/N]Support Expert Specialization Grouped GEMM (#12666 )

2025-11-11 21:23:25 -08:00

test_cutlass_w4a8_moe.py

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685 )

2025-10-17 16:49:46 -07:00

test_cutlass_w16a16_moe.py

Add support for bf16 x bf16 cutlass fused MoE (#10275 )

2025-11-24 18:49:39 -08:00

test_deepep_utils.py

Add DeepEP to CI PR Test (#5655 )

2025-05-06 17:36:03 -07:00

test_deterministic_utils.py

[Auto Sync] Update test_deterministic.py, test_deterministi... (20251024) (#12083 )

2025-10-24 22:28:01 -07:00

test_deterministic.py

[Auto Sync] Update test_deterministic.py (20260214) (#18839 )

2026-02-14 17:19:30 -08:00

test_dump_metric.py

Add unified metrics collection framework (v1) (#16064 )

2026-01-03 16:30:38 -08:00

test_dynamic_grad_mode.py

Add retry for flaky tests in CI (#4755 )

2025-03-25 16:53:12 -07:00

test_flashinfer_dispatcher.py

[NVIDIA] Add flashinfer all-to-all MOE dispatcher (#14668 )

2026-01-24 22:59:55 +08:00

test_http_server_auth.py

feat: add --admin-api-key for finer-grained endpoint auth (#15908 )

2026-01-13 20:21:55 -08:00

test_kvfp4_quant_dequant.py

feat: Add FP4 (E2M1) KV Cache Support with Quantization Utilities for MLA (#10078 )

2025-11-01 22:24:58 -07:00

test_layernorm.py

Enable mixed type LayerNorm kernel for NSA indexer (#12044 )

2025-11-03 16:50:41 -08:00

test_marlin_utils.py

Replace sglang.srt.layers.quantization.scalar_types with sgl_kernel.scalar_type (#8951 )

2025-08-13 19:41:41 -07:00

test_mm_utils.py

[Fix] SGLANG_USE_CUDA_IPC_TRANSPORT=1 and SGLANG_ENABLE_MM_SPLITTING=1 do not work at the same time. (#19915 )

2026-03-30 01:15:26 +08:00

test_programs.py

[AMD] Add AITER Custom All-Reduce (#13102 )

2025-11-12 21:53:44 -08:00

test_utils.py

Fix circular reference in CustomTestCase.__init_subclass__ (#21650 )

2026-03-29 20:38:12 -07:00

tool_call_test_runner.py

Fix parallel tool call test for speculative decoding variants (#19370 )

2026-02-26 18:31:20 -08:00

vlm_utils.py

[Misc] Tiny: Add test network timeouts and dynamic max-parallel for 5090/2-gpu runners (#21800 )

2026-03-31 18:27:39 -07:00