Yong Hoon ShinandCyrus Leung 9324e10275 Fix KV sharing fast prefill with cudagraph enabled (#28537) ...

Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

2025-11-14 11:53:42 +00:00

..

attention

[Attention] Refactor CUDA attention backend selection logic (#24794)

2025-11-11 07:40:44 -05:00

core

[KV Connector] Test async mode in scheduler tests (#28550)

2025-11-13 18:30:59 -05:00

cudagraph

[CI] Add tests for cudagraph (#27391)

2025-10-25 02:37:33 +00:00

distributed

[Test] Add non-MoE DP test coverage (#28235)

2025-11-06 20:59:57 +00:00

e2e

Fix KV sharing fast prefill with cudagraph enabled (#28537)

2025-11-14 11:53:42 +00:00

ec_connector

[Core] Encoder separation for Encode-Prefill-Decode Disaggregation (#25233)

2025-11-11 18:58:33 -08:00

engine

[Perf] Support stream interval for reducing host overhead (#27869)

2025-11-13 13:21:25 -05:00

entrypoints

[BugFix][CI/Build][ROCM] Fix import error and apply assert in appropriate case in test_struct_output_generate (#28311)

2025-11-13 22:41:29 -08:00

executor

[Core] Simplify async KV output aggregation (#28327)

2025-11-09 09:44:13 -08:00

generation

[Feature] Extend batch invariant torch.compile to B200 (#27856)

2025-11-05 10:04:49 -08:00

kv_connector

[KV Connector] Test async mode in scheduler tests (#28550)

2025-11-13 18:30:59 -05:00

kv_offload

Implement ARC KV cache eviction policy for CPU offloader (#27039)

2025-11-12 09:51:39 -08:00

logits_processors

[Bugfix] Validate custom logits processor xargs for online serving (#27560)

2025-11-05 16:53:33 +00:00

metrics

[Metrics] Refactor LoRA state tracking (#26801)

2025-11-10 16:34:36 +08:00

sample

[V0 deprecation] Remove VLLM_USE_V1 usage in most modules (#27955)

2025-11-04 20:51:16 -08:00

shutdown

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

spec_decode

[Attention] Refactor CUDA attention backend selection logic (#24794)

2025-11-11 07:40:44 -05:00

structured_output

[Bugfix] Fix llguidance backend, rollback when EOS was encountered (#25905)

2025-11-10 14:53:32 -05:00

tpu

[Core] Async scheduling + structured outputs compatibility (#26866)

2025-11-01 00:35:04 +00:00

tracing

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

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

worker

[Attention] Refactor CUDA attention backend selection logic (#24794)

2025-11-11 07:40:44 -05:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

test_oracle.py

[V0 deprecation]clean up is_v1_supported_oracle (#28116)

2025-11-06 16:05:32 +08:00

test_outputs.py

Fix cu_num_generated_tokens slicing logic in LogprobsLists.slice() method (#28214)

2025-11-09 19:11:46 +00:00

test_request.py

[Misc] Add SPDX-FileCopyrightText (#20428)

2025-07-04 07:40:42 +00:00

test_serial_utils.py

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

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

utils.py

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

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