Matthew BonanniandSandishKumarHN 757068dc65 [Bugfix][Async] Fix async spec decoding with hybrid models (#38556) ...

Signed-off-by: SandishKumarHN <sandishkumarhn@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: SandishKumarHN <sandishkumarhn@gmail.com>

2026-03-31 11:08:54 -04:00

..

attention

[ROCm] Attention selector reordering (#36702)

2026-03-25 17:42:56 +08:00

core

[Refactor] Rename WAITING_FOR_FSM to WAITING_FOR_STRUCTURED_OUTPUT_GRAMMAR (#38048)

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

cudagraph

Relocate Encoder CUDA graph manager (#38116)

2026-03-25 20:52:12 -07:00

determinism

[Bugfix] Register VLLM_BATCH_INVARIANT in envs.py to fix spurious unknown env var warning (#35007)

2026-03-23 18:31:14 -04:00

distributed

[Bugfix][CI] Skip flaky test_eagle test (#38566)

2026-03-31 09:42:37 -04:00

e2e

[Feat][Spec Decode] DFlash (#36847)

2026-03-30 15:03:15 -04:00

ec_connector

[BugFix] Fix implicit and incorrect assumption on ECConnector is_producer (#34783)

2026-03-04 15:01:30 +01:00

engine

[Test] Fix flaky race condition in test_abort_final_step (#38414)

2026-03-28 09:06:56 +00:00

entrypoints/openai

[Feature] limit thinking tokens (hard limit) (#20859)

2026-03-24 09:53:07 -07:00

executor

[Hardware][TPU] Add supports_async_scheduling() method to Executor interface so that it can be extended for Executor implementations. (#36924)

2026-03-18 12:53:28 +08:00

kv_connector

[P/D] Mooncake: Add unit tests and minor fixes for mooncake connector (#36946)

2026-03-27 09:26:40 +01:00

kv_offload

[kv_offload+HMA][7/N]: Support register_kv_caches for hybrid models (#37853)

2026-03-27 08:38:33 +03:00

logits_processors

[Feature] limit thinking tokens (hard limit) (#20859)

2026-03-24 09:53:07 -07:00

metrics

[Bugfix] Expand quantization method support in perf metrics (#37231)

2026-03-18 23:54:19 +00:00

sample

[ROCm][CI] Prep Tests For Change To ROCM_ATTN As New Default Backend On ROCm (#36025)

2026-03-09 13:27:55 -05:00

shutdown

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

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

spec_decode

[Bugfix][Async] Fix async spec decoding with hybrid models (#38556)

2026-03-31 11:08:54 -04:00

streaming_input

[Model Runner V2] Support Streaming Inputs (#37028)

2026-03-20 20:42:25 +00:00

structured_output

[Refactor] Consolidate GPT-OSS reasoning parser tests (#36915)

2026-03-16 15:53:07 -04:00

tracing

[Feature] OTEL tracing during loading (#31162)

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

worker

[HMA]Fix corner case when hybrid page_size can not be evenly divided issue (blk_size=64,tp=4) (#37467)

2026-03-30 16:47:30 +00:00

__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

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

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

utils.py

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

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