Files

T

Byron HsuandByronHsu 046cdaabaa [Sampling] Capture masks from sampler support (#36630 )

Co-authored-by: ByronHsu <ByronHsu@users.noreply.github.com>

2026-09-02 17:13:28 -07:00

4-gpu-models

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

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

8-gpu-models

[CI] Move tests onto the right CI stages (#34074 )

2026-08-31 12:39:59 -07:00

amd

[CI] Move tests onto the right CI stages (#34074 )

2026-08-31 12:39:59 -07:00

attention

Fix unified SWA: size a non-owner's v2p by the id space it must address (#37560 )

2026-09-02 16:56:18 -07:00

backends

[FlashInfer v0.6.18] add FlashInfer CuTe DSL NVFP4 W4A16 mode (#35120 )

2026-08-31 18:47:30 -07:00

bench_fn

[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

core

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

cpu

[CPU] Support FP8 KV cache (#32733 )

2026-09-02 10:20:54 +08:00

cuda_graph

[CI] Move tests onto the right CI stages (#34074 )

2026-08-31 12:39:59 -07:00

dcp

[Feature] Unified memory: support decode context parallelism for Kimi-Linear (#36890 )

2026-09-01 12:44:26 -07:00

debug_utils

[CI] Move tests onto the right CI stages (#34074 )

2026-08-31 12:39:59 -07:00

disaggregation

[Fix] Shut hicache test servers down gracefully before SIGKILL (#37194 )

2026-08-30 22:45:40 -07:00

dllm

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

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

dp_attn

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

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

dp_engine

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

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

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

2026-08-26 19:54:33 -07:00

eplb

[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

eval

[CI] Move tests onto the right CI stages (#34074 )

2026-08-31 12:39:59 -07:00

expert_pack

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

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

function_call

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

gb300

Stabilize GB300 nightly tests (#35044 )

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

gemm

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

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

hicache

[Fix] Shut hicache test servers down gracefully before SIGKILL (#37194 )

2026-08-30 22:45:40 -07:00

input_embedding

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

jit

[Diffusion] Fuse FLUX.2 gated residual normalization on Blackwell (#37112 )

2026-09-01 08:38:33 +08:00

kernels

[AMD] Enable FP4 indexer for Deepseek V4 (#37353 )

2026-09-02 09:45:08 -07:00

kv_canary

[mem_cache] Make free_swa sync-free on page_size == 1 (#36723 )

2026-09-02 14:18:22 -07:00

layers

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

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

lora

[CI] Move tests onto the right CI stages (#34074 )

2026-08-31 12:39:59 -07:00

mem_cache

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

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

mla

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

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

mlx/models_e2e

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

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

mock_model

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

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

model_loading

[CI] Move tests onto the right CI stages (#34074 )

2026-08-31 12:39:59 -07:00

models_e2e

[Feature] Unified memory: support decode context parallelism for Kimi-Linear (#36890 )

2026-09-01 12:44:26 -07:00

moe

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

musa

chore: cleanup garbage code (#29770 )

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

npu

test(npu): add DSV4-Flash / GLM-5.2 / Kimi-K3 gpqa accuracy cases (#37431 )

2026-09-01 22:00:04 +08:00

observability

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

openai_server

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

ops

[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

page_major

[unified-memory] Drop the vacated 'dense' qualifier and the restating comments (#37170 )

2026-08-31 00:54:13 -07:00

perf

[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

prefill_only

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

profiling

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

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

quant

[CI] Fix stale GPU capability test patches (#37148 )

2026-08-30 10:12:32 -07:00

radix_cache

[Radix Cache] Add Rust TreeCore backend with shared parity tests (#32710 )

2026-09-01 00:26:20 +08:00

reasoning

…

[FlashInfer v0.6.18] add FlashInfer CuTe DSL NVFP4 W4A16 mode (#35120 )

2026-08-31 18:47:30 -07:00

rotary

[rotary] Fix the fused Qwen3.5 RoPE kernel discarding mrope height and width (#34446 )

2026-08-30 15:37:40 +08:00

rust

[Rust] Rename mem-cache to sglang-radix-tree (#37290 )

2026-09-01 03:03:44 -07:00

sampling

[Sampling] Capture masks from sampler support (#36630 )

2026-09-02 17:13:28 -07:00

scheduler

[CI] Move tests onto the right CI stages (#34074 )

2026-08-31 12:39:59 -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

sessions

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

spec

[Memory] Size the CUDA graph pool from warmup measurements and fix graph-pool borrowing (#36911 )

2026-09-01 09:32:38 -07:00

stress

…

tokenizer

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

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

unit

Fix unified SWA: size a non-owner's v2p by the id space it must address (#37560 )

2026-09-02 16:56:18 -07:00

utils

[CI] Move tests onto the right CI stages (#34074 )

2026-08-31 12:39:59 -07:00

vlm

[Rust] Split and rename embedded server components (#37220 )

2026-08-31 12:28:43 -07:00

xpu

[Fix] Use real ReqKvInfo in unit-test req mocks (#37339 )

2026-08-31 20:25:51 -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.