5 people fa75d3456d [Feature][PCP] Add DeepSeek-V4.1-Flash support (#59857) ...

Signed-off-by: wangyicong <wangyicong@bytedance.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>

2026-10-15 23:17:51 -07:00

..

aux_output_connector

[BugFix][DiffusionGemma][CPU] Copy async output snapshots instead of aliasing reused buffers (#59829)

2026-10-08 19:16:51 -07:00

__init__.py

[CI/Build] Move test_utils.py to tests/utils.py (#4425)

2024-05-13 23:50:09 +09:00

conftest.py

[Core] Remove the legacy Ray compiled-graph executor (#61712)

2026-10-14 18:13:27 -07:00

eplb_utils.py

[XPU] Enable XPU eplb (#44987)

2026-09-17 13:19:13 +08:00

test_aiter_rms_fallback.py

[ROCm][Bugfix] Run the AITER AR+RMSNorm fallback test on the platform… (#61350)

2026-10-13 08:35:57 +00:00

test_ca_buffer_sharing.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

test_comm_ops.py

[Core] Release FlashInfer allreduce workspace with --enable-nccl-comm-suspend (#59360)

2026-10-10 02:26:40 +00:00

test_context_parallel.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_cpu_all_reduce.py

[Perf] Low-latency CPU all-reduce for DP metadata syncs (#61767)

2026-10-15 15:29:13 -07:00

test_custom_all_gather_reduce_scatter.py

[Perf][Distributed] Add low-SM multimem reduce-scatter for SM100/SM103 (#55072)

2026-09-25 03:27:21 +00:00

test_custom_all_reduce.py

[Distributed] Enable custom all-reduce under VLLM_BATCH_INVARIANT (#58623)

2026-10-02 02:25:48 +00:00

test_dcp_a2a.py

[DCP] Default query replication for GLM sparse attention (#50382)

2026-08-21 09:07:05 -07:00

test_dcp_direct_a2a_lse_reduce.py

[Spec Decode] Enable Gemma4 DSpark adaptive verification with FlashInfer (#57263)

2026-09-26 17:01:17 +08:00

test_distributed_oot.py

[Bugfix][MRV2] Keep input_ids on later PP stages for raw-token models (#61016)

2026-10-15 12:54:21 -07:00

test_elastic_ep.py

[Feature] Add External LB Mode Support for Elastic EP Scaling (#43202)

2026-10-15 21:29:02 -04:00

test_engram_dp_shard.py

[Feature][PCP] Add DeepSeek-V4.1-Flash support (#59857)

2026-10-15 23:17:51 -07:00

test_eplb_algo.py

[XPU] Enable XPU eplb (#44987)

2026-09-17 13:19:13 +08:00

test_eplb_events.py

[XPU] Enable XPU eplb (#44987)

2026-09-17 13:19:13 +08:00

test_eplb_execute.py

[Bugfix][EPLB] Use group-local ranks for torch P2P transfers (#55804)

2026-10-06 07:44:57 +00:00

test_eplb_fused_moe_layer_dep_nvfp4.py

[XPU] Enable XPU eplb (#44987)

2026-09-17 13:19:13 +08:00

test_eplb_fused_moe_layer.py

[XPU] Enable XPU eplb (#44987)

2026-09-17 13:19:13 +08:00

test_eplb_migration_scheduler.py

[EPLB] Add contention-aware expert migration batching (#52641)

2026-10-03 00:13:50 +00:00

test_eplb_quant_scale_consistency.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_eplb_spec_decode.py

[Chore] Use upstream Transformers DeepseekV4Config (#61392)

2026-10-15 01:08:08 -07:00

test_eplb_utils.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_events.py

[Core][Frontend] Bind KV-event publishers at port 0 and expose the bound endpoints (#55844)

2026-09-18 18:11:05 -07:00

test_expert_parallel.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

test_expert_placement.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_file_store.py

[BugFix] Use file:// rendezvous for single-node executors to eliminate startup port races (#50999)

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

test_flashinfer_pcie_ipc_all_reduce.py

[Distributed] Add opt-in FlashInfer PCIe IPC all-reduce backend (#53576)

2026-09-01 03:34:56 +00:00

test_kimi_linear_context_parallel.py

[Core][Mamba] Remove leftovers of mamba_cache_mode="all" (#60043)

2026-10-13 00:58:59 -07:00

test_kv_cache_events.py

[Core][KV Events] Echo session_id on GPU BlockStored events (#51381)

2026-09-04 02:22:50 +00:00

test_kvlayout.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

test_mnnvl_alltoall.py

[Perf][MoE] Eliminate staging from NCCL symmetric reduce-scatter (#49194)

2026-10-06 07:37:01 -07:00

test_mq_connect_ip.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_multiproc_executor.py

[XPU][UT]Using the device_control_env_var to restrict visible device on different platform (#57581)

2026-09-20 10:52:50 +08:00

test_nccl_symm_mem.py

[Perf][MoE] Eliminate staging from NCCL symmetric reduce-scatter (#49194)

2026-10-06 07:37:01 -07:00

test_node_count.py

[Chore] Separate out vllm.utils.network_utils (#27164)

2025-10-19 03:06:32 -07:00

test_packed_tensor.py

[Bugfix] Support 0-dim tensors in packed weight transfer (#52235)

2026-10-11 01:41:06 +00:00

test_pipeline_parallel.py

[Core] Remove the legacy Ray compiled-graph executor (#61712)

2026-10-14 18:13:27 -07:00

test_pipeline_partition.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_pp_cudagraph.py

[AMD][CI] Fix Pipeline + Context Parallelism test group (#46650)

2026-06-24 22:23:42 -05:00

test_pynccl.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_quick_all_reduce.py

[Perf][ROCm] Enable AITER QuickReduce + RMSNorm fusion (#48249)

2026-09-17 15:05:48 +00:00

test_ray_v2_executor_e2e.py

[Core] Remove the legacy Ray compiled-graph executor (#61712)

2026-10-14 18:13:27 -07:00

test_ray_v2_executor.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_rocm_aiter_custom_ar.py

[Perf][ROCm] Add AITER custom AG/RS (DP only) (#48247)

2026-09-11 13:19:57 +08:00

test_rocm_quick_reduce.py

[communication] [bugfix] fix quickreduce acc error in cudagraph mode (#46913)

2026-07-27 01:38:45 -07:00

test_same_node.py

create is_in_the_same_node on cpu (#26832)

2025-10-21 02:04:14 +00:00

test_sharded_rdt_plan.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_sharded_rdt_producer.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_sharded_rdt_trainer.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_shm_broadcast.py

[Bugfix][Distributed] Own SHM out-of-band buffers before releasing read slots (#61000)

2026-10-12 01:44:12 -04:00

test_shm_buffer.py

[Security] Authenticate shared-memory multimodal cache handles (#59357)

2026-09-30 05:16:26 -07:00

test_shm_storage.py

[Bugfix][Multimodal] Fix reference counting of the SHM processor cache (#59695)

2026-10-02 22:14:13 +08:00

test_split_group.py

use split_group for pytorch process group creation (#41980)

2026-06-04 14:36:07 -04:00

test_symm_mem_allreduce.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

test_torchrun_example_moe.py

use split_group for pytorch process group creation (#41980)

2026-06-04 14:36:07 -04:00

test_torchrun_example.py

use split_group for pytorch process group creation (#41980)

2026-06-04 14:36:07 -04:00

test_utils.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_weight_transfer_m2n.py

[RL] Release weight-transfer communicators without stopping inference (#61060)

2026-10-11 21:15:14 +08:00

test_weight_transfer_nccl_uid.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_weight_transfer.py

[RL] Release weight-transfer communicators without stopping inference (#61060)

2026-10-11 21:15:14 +08:00