minke.yu/sglang

Files

T

History

Liangsheng Yin 0438b16154 [mem_cache] Move kv_committed_len into ReqKvInfo (#37078 )

2026-08-29 22:42:25 -07:00

..

Add Laguna-XS-2.1 / S-2.1 NVFP4 nightly gsm8k tests (#35547 )

2026-08-29 03:34:46 -07:00

[CI] Fix nightly test failures (#34523 )

2026-08-12 15:40:20 -07:00

[AMD] Optimize Qwen3.5 MTP unified attention on gfx950 (#36330 )

2026-08-27 00:13:49 -07:00

qwen 3.8 rebase (#35758 )

2026-08-28 20:41:34 -07:00

[FlashInfer v0.6.16] Support FlashInfer CuTe DSL NVFP4 MoE quantization (#28354 )

2026-08-13 17:33:46 -07:00

[CI] Cut repeated tokenizer loads, serial subprocesses and a double scan (#36241 )

2026-08-24 18:22:43 -07:00

chunked_prefill

[Fix] Re-encode multimodal embeddings after cache mismatch (#36595 )

2026-08-27 23:24:30 +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

Support gated launch to defer startup memory allocation (#35927 )

2026-08-24 20:19:45 +08:00

[Test] Move gpqa and aime25 onto sgl-eval, drop unused eval paths (#36979 )

2026-08-29 17:36:13 -07:00

config: the dead record parameters go (#36974 )

2026-08-29 04:20:55 -07:00

[Feature] Support PP in full prefill CUDA graphs (#35451 )

2026-08-27 17:32:00 -07:00

[DCP] Drop the prefill index-selection syncs by taking each rank's rows by stride (#35084 )

2026-08-17 19:55:51 -07:00

fix(test): stabilize nightly precision regression (#34668 )

2026-08-25 20:04:52 -07:00

chore: bump mooncake version to 0.3.13 (#36493 )

2026-08-26 22:21:15 +08:00

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

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

[Feature] Coordinate FullCG prefill across DP-attention ranks (#35640 )

2026-08-26 02:16:02 -07:00

…

[Feature] Add DeepEPv2 (ElasticBuffer) MoE A2A backend (#35634 )

2026-08-26 19:54:33 -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

[CI] Remove GLM-4.1V-9B-Thinking from nightly VLM MMMU eval (#36602 )

2026-08-26 20:29:38 -07:00

Refactor JIT kernel and expert-pack directory layout (#36704 )

2026-08-29 07:41:25 +08:00

Register CPU CI for 17 e2e tests and partition xeon base-c suite (#35227 )

2026-08-24 10:49:38 +08:00

Stabilize GB300 nightly tests (#35044 )

2026-08-17 03:30:16 -07:00

Qwen3.8-27B Model Support (#34859 )

2026-08-19 16:31:43 +08:00

[AMD][CI] Limit HiCache MGSM eval concurrency on ROCm (#36308 )

2026-08-28 01:05:59 -07:00

input_embedding

Register CPU CI for 17 e2e tests and partition xeon base-c suite (#35227 )

2026-08-24 10:49:38 +08:00

[HiSparse] Support hisparse multi-step swap io kernel (#32162 )

2026-08-24 17:29:44 -07:00

[ROCm] Fix QuickReduce fp16 saturation corrupting bf16 all-reduces (106M non-finite -> 0, +0.3%) (#34484 )

2026-08-29 22:08:17 -07:00

Register CPU CI for 17 e2e tests and partition xeon base-c suite (#35227 )

2026-08-24 10:49:38 +08:00

config: a parallel size has one spelling; a patched scope declares its own (#36621 )

2026-08-27 12:56:42 -07:00

Register CPU CI for 17 e2e tests and partition xeon base-c suite (#35227 )

2026-08-24 10:49:38 +08:00

[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

[MLX] Window-bounded SWA KV storage and in-graph sampling (#34166 )

2026-08-09 21:28:51 -07:00

[Feature] Optimize TP LMHead with All-to-All (#32313 )

2026-08-17 19:55:27 -07:00

[Weight Cache] Enhance test and support EPLB (#36198 )

2026-08-26 23:11:53 -07:00

[Test] Move gpqa and aime25 onto sgl-eval, drop unused eval paths (#36979 )

2026-08-29 17:36:13 -07:00

Register CPU CI for 17 e2e tests and partition xeon base-c suite (#35227 )

2026-08-24 10:49:38 +08:00

chore: cleanup garbage code (#29770 )

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

[NPU] Chain PR test jobs and disable two DeepSeek-V4-Flash perf tests (#36672 )

2026-08-28 09:16:09 +08:00

Register CPU CI for 17 e2e tests and partition xeon base-c suite (#35227 )

2026-08-24 10:49:38 +08:00

Register CPU CI for 17 e2e tests and partition xeon base-c suite (#35227 )

2026-08-24 10:49:38 +08:00

[AMD][bugfix] Add moe_ep_size/moe_tp_size to the allreduce-fusion gate test stub (#35340 )

2026-08-25 01:24:52 -07:00

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

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

[AMD][CI] Adjust MI300 score API performance thresholds (#36290 )

2026-08-25 09:41:36 -07:00

[CP V1 Deprecation 1/5] Migrate tests to strategy-based prefill CP (#36222 )

2026-08-24 20:15:34 -07:00

Register CPU CI for 17 e2e tests and partition xeon base-c suite (#35227 )

2026-08-24 10:49:38 +08:00

[CI][AMD] Run the profiling suite without CUDA graphs on ROCm (#34452 )

2026-08-20 09:41:28 +08:00

[CI] Lower the AWQ Marlin MMLU threshold to 0.80 (#36570 )

2026-08-26 14:43:20 -07:00

[CI] Graceful teardown for the radix_cache server fixtures (#36605 )

2026-08-27 16:36:04 +08:00

…

Report per-token weight-version spans in generation meta info (#35926 )

2026-08-24 20:18:52 +08:00

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

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

Rainj me/rust server refactor2 (#35239 )

2026-08-21 16:37:02 -07:00

[AMD][CI] Stabilize PyTorch sampling backend test on ROCm (#36307 )

2026-08-26 18:44:10 -07:00

config: six more runtime readers ask the bags (#36973 )

2026-08-29 04:19:14 -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

Register CPU CI for 17 e2e tests and partition xeon base-c suite (#35227 )

2026-08-24 10:49:38 +08:00

config: six more runtime readers ask the bags (#36973 )

2026-08-29 04:19:14 -07:00

…

[CI] Route mmlu and GB300 MMMU-Pro evals through sgl-eval (#34477 )

2026-08-12 19:33:21 -07:00

[mem_cache] Move kv_committed_len into ReqKvInfo (#37078 )

2026-08-29 22:42:25 -07:00

config: the resolution pipeline moves out of the record (#36789 )

2026-08-28 10:17:24 -07:00

[BugFix][VLM] keep Qwen3-VL MoE inference deepstack order (#34690 )

2026-08-28 17:02:16 +08:00

[mem_cache] Move kv_committed_len into ReqKvInfo (#37078 )

2026-08-29 22:42:25 -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.