3 people cfbee3d0e7 [CLI env var] Add VLLM_FLASH_ATTN_MAX_NUM_SPLITS_FOR_CUDA_GRAPH in env variables (#25274) ...

Signed-off-by: qqma <qqma@amazon.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: qqma <qqma@amazon.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

2025-09-22 10:37:43 -07:00

..

attention

[V1] Add sliding window support to Flex Attention backend (#24089)

2025-09-21 05:08:07 +00:00

core

[Hybrid Allocator] Support full attention with different hidden size (#25101)

2025-09-19 23:43:59 -07:00

cudagraph

[CLI env var] Add VLLM_FLASH_ATTN_MAX_NUM_SPLITS_FOR_CUDA_GRAPH in env variables (#25274)

2025-09-22 10:37:43 -07:00

e2e

[CI] Revert back prepare_prompts and check_answers (#25087)

2025-09-17 11:03:16 -07:00

engine

[V0 Deprecation] Remove async_output_proc, preemption mode, delay factor (#25334)

2025-09-21 08:52:32 -07:00

entrypoints

[Chore] Cleanup guided namespace, move to structured outputs config (#22772)

2025-09-18 09:20:27 +00:00

executor

[Doc]: fix typos in Python comments (#24077)

2025-09-02 02:38:55 -07:00

kv_connector

[KV offload][4/N] Offloading KV connector (#22595)

2025-09-19 19:07:17 +00:00

kv_offload

[KV offload][3/N] Add worker-side CPU support (#21448)

2025-09-19 09:53:45 -07:00

logits_processors

[V1] Logits processor docs (#22919)

2025-09-17 11:53:12 -07:00

metrics

[Misc] Have AsyncLLM custom_stat_loggers extend default logger list (#20952)

2025-09-04 14:25:30 -07:00

sample

Move ModelConfig from config/__init__.py to config/model.py (#25252)

2025-09-19 16:22:33 +00:00

shutdown

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

spec_decode

[Spec Decode] Efficient padded speculation (#24539)

2025-09-18 01:07:24 -04:00

structured_output

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

tpu

[TPU] Deprecate xm.mark_step in favor of `torch_xla.sync (#25254)

2025-09-22 10:12:57 +00:00

tracing

[V0 Deprecation] Remove V0 Tracing & Metrics tests (#25115)

2025-09-17 19:40:44 -07:00

worker

[Core] Use CpuGpuBuffer for block table tensors (#24795)

2025-09-16 19:18:06 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

test_async_llm_dp.py

[BugFix] Async scheduling and PP compatibility with DP (#23770)

2025-08-29 08:17:27 -07:00

test_external_lb_dp.py

[Frontend] Pass API server count to each process (#23717)

2025-09-20 01:15:19 +08:00

test_hybrid_lb_dp.py

[Frontend] Pass API server count to each process (#23717)

2025-09-20 01:15:19 +08:00

test_internal_lb_dp.py

[Frontend] Pass API server count to each process (#23717)

2025-09-20 01:15:19 +08:00

test_kv_sharing.py

[Doc]: fix typos in Python comments (#24077)

2025-09-02 02:38:55 -07:00

test_metrics_reader.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_oracle.py

[V0 Deprecation] Remove async_output_proc, preemption mode, delay factor (#25334)

2025-09-21 08:52:32 -07:00

test_request.py

[Misc] Add SPDX-FileCopyrightText (#20428)

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

test_serial_utils.py

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

2025-08-18 09:52:00 +00:00

test_utils.py

Support encoder-only models without KV-Cache (#21270)

2025-07-26 21:09:52 +08:00