3 people 1652d0ac42 [Bugfix] Poll shared-memory notifications while readers stay busy (#1306) ...

Ported from ReVolta:
https://github.com/Leonccaa/ReVolta/commit/caa5b4de6ef0111f0c0820a8d3bb8f1bdcb15471

Original vLLM sources, adapted in ReVolta:
https://github.com/vllm-project/vllm/pull/63165

Signed-off-by: Leonccaa <166551845+Leonccaa@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Codex <codex@openai.com>

2026-11-05 21:28:08 +08:00

..

__init__.py

…

conftest.py

…

eplb_utils.py

…

test_ca_buffer_sharing.py

…

test_collective_policy_cuda.py

[Core] Bind graph and collective policies to engine resources

2026-10-10 01:02:39 +08:00

test_comm_ops.py

…

test_context_parallel.py

…

test_custom_all_reduce_allocator.py

…

test_custom_all_reduce_dispatch.py

[Bugfix][Distributed] Verify P2P before provisioning compact collectives without custom all-reduce (#1219)

2026-10-28 10:28:42 +08:00

test_custom_all_reduce.py

[Doc] Close Phase C with collective operator acceptance

2026-10-10 01:26:50 +08:00

test_dcp_a2a.py

…

test_distributed_oot.py

…

test_elastic_ep.py

…

test_ep_communicator_admission.py

[Core] Bound original GGUF storage and host KV state on SM70

2026-10-11 01:13:11 +08:00

test_eplb_algo.py

…

test_eplb_events.py

…

test_eplb_execute.py

…

test_eplb_fused_moe_layer_dep_nvfp4.py

…

test_eplb_fused_moe_layer.py

…

test_eplb_spec_decode.py

…

test_eplb_utils.py

…

test_events.py

…

test_expert_parallel.py

…

test_expert_placement.py

…

test_group_coordinator_timeout.py

…

test_inplace_all_reduce_default.py

[Bugfix] Keep the pynccl all-reduce out-of-place by default (#1284)

2026-10-28 13:43:01 +08:00

test_kv_cache_events.py

…

test_kvlayout.py

…

test_mnnvl_alltoall.py

…

test_mq_connect_ip.py

…

test_multi_node_assignment.py

…

test_multiproc_executor.py

…

test_nccl_graph_register_default.py

…

test_nccl_symm_mem_allreduce.py

…

test_node_count.py

…

test_packed_tensor.py

…

test_pipeline_parallel.py

…

test_pipeline_partition.py

[Core] Resolve runtime policy per engine at ordered defaults

2026-10-09 22:42:41 +08:00

test_pp_cudagraph.py

…

test_pynccl.py

…

test_quick_all_reduce.py

…

test_ray_v2_executor_e2e.py

…

test_ray_v2_executor.py

…

test_rocm_quick_reduce.py

…

test_same_node.py

…

test_shm_broadcast.py

[Bugfix] Poll shared-memory notifications while readers stay busy (#1306)

2026-11-05 21:28:08 +08:00

test_shm_buffer.py

…

test_shm_storage.py

[Bugfix][Multimodal] Stop the shm processor cache from pinning items for good (#1200)

2026-10-28 10:31:46 +08:00

test_sm70_medium_all_reduce.py

[Core] Bind graph and collective policies to engine resources

2026-10-10 01:02:39 +08:00

test_sm70_ring_capabilities.py

[Core] Bind graph and collective policies to engine resources

2026-10-10 01:02:39 +08:00

test_sm70_tp4_push_gemma_norm.py

[Perf][SM70][Distributed] Fused TP4 push all-reduce + Gemma RMSNorm for 16/24/32 verifier rows (#1292)

2026-10-28 21:35:19 +08:00

test_sm70_tp8_hierarchical_custom_all_reduce.py

[Core] Bind graph and collective policies to engine resources

2026-10-10 01:02:39 +08:00

test_static_tensor_transfer.py

…

test_symm_mem_allreduce.py

…

test_torchrun_example_moe.py

…

test_torchrun_example.py

…

test_utils.py

…

test_weight_transfer.py

…