sglang

test_batch_result_processor_hidden_states.py

[diffusion] model: support minimax-h3 (#33275 )

2026-08-02 22:32:37 +08:00

test_batch_result_processor_mamba_boundary.py

[srt] Reuse batched Mamba boundary mask (#33477 )

2026-08-09 16:47:05 +08:00

test_batch_result_processor_spec_grammar.py

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

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

test_customized_info_streaming.py

[AMD] Register 2 hardware-agnostic 1-GPU PR tests for AMD CI (#30207 )

2026-07-07 14:46:22 -07:00

test_data_parallel_controller.py

[1/N] elastic-ep: Add runtime EP scale-up (#30164 )

2026-07-16 15:53:44 -07:00

test_embed_overrides.py

[CI] Move CPU-only unit tests to the CPU suite and trim dead 5090 registrations (#33654 )

2026-08-05 01:43:29 -07:00

test_fanout_communicator.py

[Fix] Serialize FanOutCommunicator queueing calls with a FIFO-fair asyncio.Lock (#30606 )

2026-07-09 00:04:43 -07:00

test_finish_length_speculative.py

[bugfix] Stop/EOS inside a spec accept run beats the max_new_tokens finish (#33758 )

2026-08-07 15:18:14 -07:00

test_flat_raw_top_logprobs.py

[CI] Fix runtime context setup in flat logprob tests (#33179 )

2026-07-31 22:46:24 -07:00

test_grammar_stop_speculative.py

Fix stop boundaries for grammar-constrained speculative decoding (#31738 )

2026-07-20 17:55:27 -07:00

test_hidden_state_server_mode.py

[Feature] Support return_hidden_states="last" (#30177 )

2026-08-02 15:09:33 +08:00

test_hisparse_unit.py

Introduce req.kv container for coupled owned kv field lifecycle (#29427 )

2026-07-15 14:40:38 +08:00

test_io_struct.py

Revert parallel request lifecycle tracking from #32588 (#34160 )

2026-08-09 03:10:02 -07:00

test_kv_page_invariants.py

Introduce req.kv container for coupled owned kv field lifecycle (#29427 )

2026-07-15 14:40:38 +08:00

test_load_snapshot_backends.py

Add prefill and decode load counters to LoadSnapshot (#32245 )

2026-07-24 14:04:54 -07:00

test_lora_update_result_merge.py

Split #32584 into 2/2: [LoRA] Shard attention LoRA by attn-TP and allow dynamic LoRA with dp attention (#32708 )

2026-07-31 15:37:13 -07:00

test_mm_hashes.py

[CI] Move CPU-only unit tests to the CPU suite and trim dead 5090 registrations (#33654 )

2026-08-05 01:43:29 -07:00

test_mm_process_config.py

Add CUDA VMM multimodal feature transport (#33899 )

2026-08-07 13:39:54 -07:00

test_mm_utils_split.py

model: support nvidia/LocateAnything-3B (#28958 )

2026-06-30 00:16:42 +08:00

test_msgpack_ipc_roundtrip.py

[LoRA] 1/n Per-rank tensor serialization for load_lora_adapter_from_tensors under dp_size > 1 (#32580 )

2026-07-28 14:28:56 -07:00

test_multi_tokenizer_mixin.py

Return top-p/top-k sampling mask/nucleas (#27408 )

2026-07-13 17:58:51 -05:00

test_output_streamer_customized_info.py

pad customized_info for mixed output batches (#29842 )

2026-07-02 12:07:58 +08:00

test_pp_cp_rank_offsets.py

Support scheduler_recv_interval (recv skipper) under DP-attention (#30457 )

2026-07-14 14:02:58 -07:00

test_prefill_adder.py

Move SWA chunk-cap hatch tests into the registered suite (#33975 )

2026-08-07 17:49:07 +08:00

test_priority_scheduling_disaggregation.py

[CI] Move CPU-only unit tests to the CPU suite and trim dead 5090 registrations (#33654 )

2026-08-05 01:43:29 -07:00

test_profile_merger_http_api.py

[CI] Move CPU-only unit tests to the CPU suite and trim dead 5090 registrations (#33654 )

2026-08-05 01:43:29 -07:00

test_retraction_order.py

[Scheduler] Enable decode retraction ordering under speculative decoding (#32023 )

2026-07-23 00:42:56 -07:00

test_schedule_batch_out_of_place.py

Avoid mutating ScheduleBatch fields in place (#30672 )

2026-07-15 14:27:08 +08:00

test_schedule_batch_prepare_for_decode.py

Remove dead ScheduleBatch fields and avoid inplace seq_lens bump (#30669 )

2026-07-15 14:23:31 +08:00

test_schedule_batch_req_pool_indices.py

[Feature] Support return_hidden_states="last" (#30177 )

2026-08-02 15:09:33 +08:00

test_scheduler_chunked_req_gate.py

Introduce NgramEmbeddingManager component (#31154 )

2026-07-14 15:58:08 +08:00

test_scheduler_decision_batch_params.py

Avoid implicit field-based side channel in Scheduler planning (#29408 )

2026-07-10 08:55:51 +08:00

test_scheduler_flush_cache.py

[CI] reduce CPU CI scope with base-c suite (#28623 )

2026-06-24 16:18:06 +08:00

test_scheduler_hicache_attach.py

config: keep runtime hicache and weight-version updates off ServerArgs (#33336 )

2026-08-02 21:23:38 -07:00

test_scheduler_init_req_max_new_tokens.py

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

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

test_scheduler_pause_generation.py

Rewrite pause_generation retract path as req-level release and requeue for clarity (#30675 )

2026-07-15 14:32:12 +08:00

test_scheduler_recv_skipper.py

[misc] Move SchedulerRecvSkipper into scheduler_components (#31222 )

2026-07-14 16:35:04 -07:00

test_scheduler_timeouts.py

[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

test_stop_str_speculative.py

fix(schedule_batch): trim stop string when EOS matches in the same step (#28802 )

2026-06-22 13:14:00 -07:00

test_tokenizer_config_updates.py

config: keep runtime hicache and weight-version updates off ServerArgs (#33336 )

2026-08-02 21:23:38 -07:00

test_tokenizer_manager_rid_cleanup.py

Revert parallel request lifecycle tracking from #32588 (#34160 )

2026-08-09 03:10:02 -07:00

test_trim_matched_stop.py

Fix spec v2 stop output boundary (#25980 )

2026-06-09 00:32:21 -07:00

test_vocab_boundary_finish.py

[misc] Remove unit test cases that fail the admission criteria (round 3) (#30713 )

2026-07-09 19:42:51 -07:00