Files

T

Yuan Luoandluoyuan.luo 3340f4e3da [GDN][KDA][mem_cache] int8 checkpoint pool for the linear-attn prefix cache (#28185 )

Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>

2026-06-17 20:41:46 -07:00

4-gpu-models

[CI] Fix GB300 TestDummyWithSBO crash: disable NaN assert and coredump for dummy weights (#27955 )

2026-06-11 14:17:03 -07:00

8-gpu-models

[Spec] Retire Spec V1 (#27964 )

2026-06-11 16:15:15 -07:00

amd

[AMD] Fix deepseek-v4 mtp accept length issue (#28520 )

2026-06-17 11:13:55 -07:00

ascend

[Refactor] Cuda Graph Runner/Backend Refactor (#23906 )

2026-06-09 21:36:57 -07:00

attention

[misc] Trim dead code in trtllm_mha page-table backend; reuse eager page-table buffer (#28578 )

2026-06-17 18:36:22 -07:00

backends

[RL] Fix FlashInfer TRTLLM MXFP8 dense weight layout (#28459 )

2026-06-17 10:33:35 +00:00

bench_fn

Fix multimodal synthetic benchmark prompt generation to exclude special tokens (#26864 )

2026-06-04 22:27:43 +00:00

chunked_prefill

Fix PP is_fully_idle missing in-flight microbatches (#27446 )

2026-06-07 17:38:26 +08:00

constrained_decoding

[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

core

[AMD] Fix CI base-a fwd_occupancy: disable SGLANG_SANITIZE_NAN_LOGITS in AMD CI (#28075 )

2026-06-12 14:14:34 -07:00

[2/n] [CP] Add context parallel strategy abstractions (#27313 )

2026-06-16 00:20:04 -07:00

cpu

Add Arm64 INT8 MoE test coverage (#25007 )

2026-06-10 10:36:57 +08:00

cuda_graph

[Feature] Spec V2 DFlash Support (#23000 )

2026-06-10 19:27:42 -07:00

debug_utils

[CI] add Precision Regression Test on Nightly Run CI (#26902 )

2026-06-14 12:43:57 +08:00

disaggregation

Add DeepSeek V4 MTP acceptance length checks (#28098 )

2026-06-12 18:53:20 -07:00

dllm

[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

dp_attn

[AMD] Feat/dp moe reduce scatter (#28216 )

2026-06-16 18:12:39 -07:00

dp_engine

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

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

[Spec] Retire Spec V1 (#27964 )

2026-06-11 16:15:15 -07:00

eplb

LPLB: linear-programming load balancer for MoE expert parallelism (#24515 )

2026-06-16 10:19:42 -07:00

eval

test: fix gemma GSM8K thresholds in nightly text eval (#27342 )

2026-06-08 19:58:42 -07:00

function_call

[Xeon] CPU CI enhancement for Intel Xeon platforms (#24649 )

2026-05-28 10:49:04 +08:00

gb300

[Spec] Retire Spec V1 (#27964 )

2026-06-11 16:15:15 -07:00

hicache

[CI]: Fix CI Stage for 3fs backend test (#27388 )

2026-06-06 00:38:03 +08:00

input_embedding

Refactor Req.fill_ids into full_untruncated_fill_ids + fill_len with equivalence (#26637 )

2026-06-08 14:52:18 +08:00

jit

Deepseek v4: support mixed dtype compression states (#27277 )

2026-06-17 00:56:41 -07:00

kernels

Add get_parallel(): a structured accessor for parallel-topology state (#28567 )

2026-06-17 20:23:43 -07:00

kv_canary

[Spec][test] fix(kv_canary): assert draft-extend-v2 oracle tokens in token_oracle test (#28325 )

2026-06-15 19:14:09 -07:00

layers

Add get_parallel(): a structured accessor for parallel-topology state (#28567 )

2026-06-17 20:23:43 -07:00

lora

[LoRA] Fix chunked SGMV (csgmv) CUDA graph segment replay (#28371 )

2026-06-16 19:19:07 -07:00

mla

Support spec v2 for FlashMLA speculative decoding (#24640 )

2026-05-19 15:23:17 -07:00

mock_model

[AMD] ci: add label-gated extra-a tier (kv_canary + mock_model unit tests) (#27822 )

2026-06-12 15:12:56 -07:00

model_loading

[Refactor] Cuda Graph Runner/Backend Refactor (#23906 )

2026-06-09 21:36:57 -07:00

models

[AMD] ci: register 8 framework / unit tests to run on AMD CI (#25939 )

2026-06-10 08:41:22 -07:00

models_e2e

[HiCache]Asymmetric pool support direct backend (#28446 )

2026-06-16 13:17:57 -07:00

moe

correct allreduce fusion and dummy_run alignment in SCATTERED MLP mode (moe_dense_tp_size=1) (#19918 )

2026-05-22 19:18:25 -07:00

musa

[MUSA][23/N] CI: Fix torchada preflight lock cleanup and add LLM server smoke test (#27242 )

2026-06-08 08:45:16 -07:00

observability

[observability] add Ray metric backend wrappers (#26252 )

2026-06-17 19:41:53 -07:00

openai_server

fix(frontend): return HTTP 400 for out-of-vocabulary token_ids_logprob (#28088 )

2026-06-12 17:18:26 -07:00

ops

[AMD] Update test_aiter_allgather_amd.py data types alignment between benchmark aiter and custom all-reduce kernel (#27815 )

2026-06-17 00:48:15 -07:00

perf

[Spec] Retire Spec V1 (#27964 )

2026-06-11 16:15:15 -07:00

[CI] Split PP tests into base and extra suites (#26648 )

2026-05-29 12:15:27 +08:00

prefill_only

fix(fa3): no NaN embeddings with fa_skip_kv_cache under piecewise CUDA graph (#27343 )

2026-06-15 13:46:22 -07:00

profiling

[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

quant

[ci] add kimi nvfp4 nightly tests (#28467 )

2026-06-16 16:49:51 -07:00

radix_cache

[GDN][KDA][mem_cache] int8 checkpoint pool for the linear-attn prefix cache (#28185 )

2026-06-17 20:41:46 -07:00

reasoning

[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

[RL] Fix FlashInfer TRTLLM MXFP8 dense weight layout (#28459 )

2026-06-17 10:33:35 +00:00

rotary

[misc] CI hygiene: enforce __main__ entry, drop silent-skipped tests, fix rerun-test protoc (#23305 )

2026-04-20 21:16:24 -07:00

sampling

[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

scheduler

[AMD] register 4 2-gpu tests to stage-b-test-2-gpu-large-amd (#28344 )

2026-06-16 21:58:34 -07:00

scripted_runtime

Add scripted-runtime unit, core integration, and chunked-prefill tests (#27413 )

2026-06-06 09:08:35 +08:00

sessions

[Spec] Retire Spec V1 (#27964 )

2026-06-11 16:15:15 -07:00

spec

[Test] Fold EAGLE return_hidden_states regression into spec triton suite (#28577 )

2026-06-17 16:42:02 -07:00

stress

Add stress test workflow (#13937 )

2025-11-26 13:24:39 -08:00

tokenizer

[CI] Enforce modern stage=/runner_config= form for dispatchable test suites (#28108 )

2026-06-12 17:32:54 -07:00

unit

Add get_parallel(): a structured accessor for parallel-topology state (#28567 )

2026-06-17 20:23:43 -07:00

utils

[CI] Reclaim leaked /dev/shm segments on server startup (#28089 )

2026-06-15 16:14:08 -07:00

vlm

[CI] Enforce modern stage=/runner_config= form for dispatchable test suites (#28108 )

2026-06-12 17:32:54 -07:00

xpu

test(xpu): add multi-feature and embedding stage-b tests (#27861 )

2026-06-12 14:36:28 +08:00

README.md

[CI] Add READMEs for unit test directory structure (#20626 )

2026-03-15 20:27:05 +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/`, `ascend/`	Vendor GPU

See unit/README.md for unit test conventions.