minke.yu/sglang

Files

T

History

Ke Bao ce84df0fa1 Fix deterministic inference for Inkling (#33417 )

2026-08-08 07:48:15 +08:00

..

Fix broken Nemotron DP attention (#33123 )

2026-08-05 14:27:05 -07:00

fix(gdn): skip the -1 padding sentinel in the chunked extend kernel (#33810 )

2026-08-06 18:48:47 -07:00

[CI] Remove profiling from nightly tests (#33832 )

2026-08-06 01:16:08 -07:00

Install DeepEP from release wheels (#33932 )

2026-08-07 15:38:44 -07:00

[Test] Replace NVFP4 MoE runner backend e2e matrix with a layer-level unit test (#33611 )

2026-08-04 16:03:29 -07:00

Fix serving benchmark post-warmup cache flush race (#33663 )

2026-08-06 15:27:10 +00:00

chunked_prefill

[VLM] split multimodal scheduling from mm_utils (#32415 )

2026-08-05 20:24:12 +08:00

constrained_decoding

[CI] Fold duplicate-server suites and prune the retract matrix on 1-gpu-5090 (#33745 )

2026-08-05 12:41:51 -07:00

[Build] Add srt_empty extra group for device-agnostic install (#31300 )

2026-08-05 13:17:46 -07:00

Install DeepEP from release wheels (#33932 )

2026-08-07 15:38:44 -07:00

[CI] Bound the CUDA graph capture range in test launches and lift the spec fixture's admission cap (#33776 )

2026-08-05 20:00:30 -07:00

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944 )

2026-08-07 01:22:22 -07:00

config: route DCP topology reads through get_parallel() (#33925 )

2026-08-07 14:53:54 -07:00

[Test] Route GEMM backend UTs through real layer modules and weight loaders (#33615 )

2026-08-04 20:53:26 -07:00

Install DeepEP from release wheels (#33932 )

2026-08-07 15:38:44 -07:00

[dLLM] Make FDFO a framework capability for all dLLM algorithms (#27551 )

2026-07-11 11:05:05 +08:00

[Fix] Resolve VLM test image placeholders from the model's own chat template (#33509 )

2026-08-04 02:01:39 -07:00

[Test] split test/registered/distributed/ into topic folders (#26240 )

2026-05-24 17:02:07 -07:00

Install DeepEP from release wheels (#33932 )

2026-08-07 15:38:44 -07:00

[Kernel] Phase 4 batch-3: migrate tangled JIT subsystems + new groups into kernels.ops (RFC #29630 ) (#32045 )

2026-07-22 21:15:03 +08:00

Fix Mistral GSM8K chat eval (#27757 )

2026-07-09 21:08:48 -07:00

[Kimi K3] Add reasoning, tool-call, and OpenAI serving support (#33025 )

2026-08-01 14:57:23 -07:00

[CI] Remove profiling from nightly tests (#33832 )

2026-08-06 01:16:08 -07:00

[Fix] Reject online weight updates while the HPC-Ops router GEMM split cache is active (#31943 )

2026-07-24 19:30:13 +08:00

[Fix] Release hierarchical cache host pool on graceful shutdown (#31746 )

2026-07-19 22:27:29 -07:00

input_embedding

[misc] Use --cuda-graph-max-bs-decode in tests, examples, and docs (#29591 )

2026-06-28 18:38:28 -07:00

[MXFP8] Use FlashInfer CUTLASS for dense GEMM on SM120, delete Triton path (#33208 )

2026-08-07 14:30:43 -07:00

[UnifiedTree]: move /mem_cache/unifed_cache_component dir to /mem_cache/unified_cache (#32484 )

2026-07-28 16:28:21 +08:00

Revert "Add flashinfer rmsnorm + quant fusion support SM90, SM100, SM120" (#33455 )

2026-08-03 19:03:56 -07:00

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944 )

2026-08-07 01:22:22 -07:00

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944 )

2026-08-07 01:22:22 -07:00

[CI] Merge tokenizer worker tests and drop redundant triton attention e2e (#33641 )

2026-08-05 11:55:11 -07:00

[Apple Silicon] [CI] Move the MLX lane to the check-changes + pr-gate composite (#30121 )

2026-07-10 22:00:15 -07:00

[Kernel] Phase 4 batch-3: migrate tangled JIT subsystems + new groups into kernels.ops (RFC #29630 ) (#32045 )

2026-07-22 21:15:03 +08:00

[AMD] Move test_load_weights_from_remote_instance.py to extra CI (#33809 )

2026-08-06 01:57:31 -07:00

Fix deterministic inference for Inkling (#33417 )

2026-08-08 07:48:15 +08:00

[Test] Route GEMM backend UTs through real layer modules and weight loaders (#33615 )

2026-08-04 20:53:26 -07:00

chore: cleanup garbage code (#29770 )

2026-07-02 16:14:01 +08:00

migrate NPU PR/nightly test cases to a3-560T (#33346 )

2026-08-05 01:17:58 +08:00

[Observability] Add startup, memory, and hybrid SWA diagnostics (#33375 )

2026-08-04 12:50:09 -07:00

Responses support (#32689 )

2026-08-07 13:21:46 -07:00

config: route parallel config-leaf reads through get_parallel() (#33170 )

2026-08-01 08:58:39 -07:00

feat(mem_cache): page-major (layer-major within a page) KV/state layout (#29533 )

2026-06-29 14:49:54 -07:00

[CI] Remove profiling from nightly tests (#33832 )

2026-08-06 01:16:08 -07:00

ci: lower VL PP gsm8k threshold to 0.60 (0.65 has zero margin on H100) (#31702 )

2026-07-19 15:41:12 -07:00

[CI] Collapse the EAGLE launch matrix and the scoring engine boots on the per-commit runners (#33756 )

2026-08-05 16:43:19 -07:00

[CI] Rename basic CI stage-a/b/c -> base-a/b/c for symmetry with extra CI (#25420 )

2026-05-15 18:26:55 -07:00

[CI] Remove profiling from nightly tests (#33832 )

2026-08-06 01:16:08 -07:00

[HiCache] Support packed and sidecar draft caches for MTP/EAGLE/DSpark (#30393 )

2026-08-06 14:31:11 +08:00

[CI] Rename basic CI stage-a/b/c -> base-a/b/c for symmetry with extra CI (#25420 )

2026-05-15 18:26:55 -07:00

Install DeepEP from release wheels (#33932 )

2026-08-07 15:38:44 -07:00

[rotary] Rebuild the shared RoPE cache entry when its buffers are dead (#33575 )

2026-08-04 17:24:42 -07:00

support rust sglang server (#29799 )

2026-07-31 11:56:31 -07:00

Fix flaky test_sampling_mask: mask length can legitimately be top_k + 1 (#32410 )

2026-07-25 16:05:57 -07:00

[CI] Fold duplicate-server suites and prune the retract matrix on 1-gpu-5090 (#33745 )

2026-08-05 12:41:51 -07:00

scripted_runtime

[AMD] Register 2 CPU-bound 1-GPU tests (phase_checker, scripted_runtime_core) for AMD PR CI (#30446 )

2026-07-08 14:04:23 -07:00

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944 )

2026-08-07 01:22:22 -07:00

[CI] Bound the CUDA graph capture range in test launches and lift the spec fixture's admission cap (#33776 )

2026-08-05 20:00:30 -07:00

…

[CI] Fold duplicate-server suites and prune the retract matrix on 1-gpu-5090 (#33745 )

2026-08-05 12:41:51 -07:00

[Laguna] fix YaRN mscale double-application in rope config (#33558 )

2026-08-07 16:46:08 -07:00

[Fix] Judge the phase-checker device-assert test by its FAIL line, not the exit code (#34017 )

2026-08-07 16:19:05 -07:00

[Fix] Judge the phase-checker device-assert test by its FAIL line, not the exit code (#34017 )

2026-08-07 16:19:05 -07:00

Fix DeepSeek-OCR batching crash on variable local-crop counts (#33214 )

2026-08-05 18:39:19 -07:00

README.md

Add pr tests (#31952 )

2026-08-01 15:03:21 +08:00

README.md

Registered Tests

Tests under this directory are auto-discovered by run_suite.py via CI registration decorators.

Where Should I Put My New Test?

No server / engine launch required

What you're testing	Directory	Requires
Component logic in isolation (cache, scheduler, config, parser, etc.)	`unit/<module>/`	CPU or GPU
CUDA kernel correctness	`kernels/`	GPU

Server / engine launch required (E2E)

What you're testing	Directory	Requires
Model inference correctness	`models/`, `4-gpu-models/`, `8-gpu-models/`	GPU
Feature-specific (OpenAI API, LoRA, speculative, distributed, VLM, etc.)	`openai_server/`, `lora/`, `spec/`, `distributed/`, ...	GPU
Benchmarks (performance, accuracy, stress)	`benchmark/`	GPU
Platform-specific	`amd/`, `npu/`	Vendor GPU

See unit/README.md for unit test conventions.