Nicolò Lucchesi 5672d100ed [KV Connector][NIXL][Bugfix] Fix NIXL handshake failures not honoring kv_load_failure_policy (#40364) ...

When NIXL handshake fails (e.g., due to compatibility hash mismatch
between prefill and decode instances), requests fail with "engine dead"
error instead of gracefully falling back to local recomputation as configured
by kv_load_failure_policy='recompute'.

Signed-off-by: NickLucche <nlucches@redhat.com>

2026-05-11 09:37:21 +00:00

..

attention

[Misc] Replace mamba_type string literals with MambaAttentionBackendEnum (#41188)

2026-05-11 03:59:36 +00:00

core

[Core] Simplify handling of scheduler_reserve_full_isl option (#41064)

2026-04-30 18:10:00 -07:00

cudagraph

[Bugfix] Fix spawn_new_process_for_each_test silently swallowing test failures (#41423)

2026-05-06 11:17:15 -04:00

determinism

[vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823)

2026-05-01 23:41:15 -04:00

distributed

[Bug] Fix status update address for non-MOE model within external dp mode (#40839)

2026-05-04 16:37:16 -07:00

e2e

[Attention][Cleanup] Remove tree attention (#42121)

2026-05-08 18:36:19 -07:00

ec_connector

[Docs] Fix broken local links (#42160)

2026-05-10 01:15:38 -07:00

engine

fix nixl side-channel host selection (#41806)

2026-05-11 07:40:37 +00:00

executor

[Bugfix] Fix Ray compiled-DAG SHM channel stalls by detaching zero-copy np.ndarray logprobs buffers (#35736)

2026-04-16 23:49:29 +08:00

kv_connector

[KV Connector][NIXL][Bugfix] Fix NIXL handshake failures not honoring kv_load_failure_policy (#40364)

2026-05-11 09:37:21 +00:00

kv_offload

[KV Offload] Pass ReqContext to touch(), complete_load(), and complete_store() (#41366)

2026-05-10 15:09:25 +03:00

logits_processors

[Bugfix] Fix LOGITPROC_SOURCE_ENTRYPOINT test to use spawn-compatible dist-info registration for XPU/ROCm (#42040)

2026-05-09 12:32:04 +08:00

metrics

[Bugfix][Metrics] Fix RayPrometheusMetric.labels() returning shared labeled child (#40840)

2026-05-01 08:43:39 +01:00

sample

[ROCm][CI] Align spec decode logprob test prefill settings (#41335)

2026-05-04 04:33:29 +00:00

shutdown

replace cuda_device_count_stateless() to current_platform.device_count() (#37841)

2026-03-31 22:32:54 +08:00

simple_kv_offload

[ROCm] Enable SimpleCPUOffloadConnector on ROCm (#40549)

2026-05-06 20:52:02 -07:00

spec_decode

[Attention][Cleanup] Remove tree attention (#42121)

2026-05-08 18:36:19 -07:00

streaming_input

[Reasoning] Support for speculative decoding with thinking budget (#34668)

2026-04-29 06:14:52 +00:00

structured_output

[Bugfix] Pass reasoning parser kwargs to structured output (#41199)

2026-04-30 23:38:02 -07:00

tracing

[Feature] OTEL tracing during loading (#31162)

2026-02-05 16:59:28 -08:00

worker

[Bugfix] Fix token loss in PP mode which causes degraded accuracy (#41133)

2026-05-06 14:07:32 -04:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

2024-11-11 23:05:38 +00:00

test_oracle.py

[Docs] Clean up speculators docs (#34065)

2026-02-18 13:48:11 -08:00

test_outputs.py

[BugFix] Fix spec decoding max_tokens scheduling perf issue (#29542)

2025-11-28 20:52:23 +08:00

test_request.py

[Refactor] Rename WAITING_FOR_FSM to WAITING_FOR_STRUCTURED_OUTPUT_GRAMMAR (#38048)

2026-03-25 11:41:44 -04:00

test_serial_utils.py

Add tensor IPC transfer mechanism for multimodal data (#32104)

2026-03-21 20:10:20 +00:00

test_tensor_ipc_queue.py

[Test] Refactor hard coded device string in test files under compile/quantization/models/model_executor folders (#38901)

2026-04-15 11:02:35 +08:00

utils.py

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

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