Tyler Michael Smith 4cc78c9d5d [Core] Freeze garbage collector in workers after model initialization (#44363) ...

Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>

2026-06-04 08:39:04 -07:00

..

attention

[DSv4] Adding TRTLLM gen attention kernel (#43827)

2026-06-04 07:35:09 -07:00

core

[PD][Nixl] Mamba prefix caching mode support (#42554)

2026-06-04 06:41:46 -07:00

engine

[KVCache] Support Pluggable KVCacheSpec (#37505)

2026-06-03 09:05:16 -07:00

executor

[Core] Move max_concurrent_batches to VllmConfig (#44274)

2026-06-02 08:57:25 -07:00

kv_offload

[SharedOffloadRegion] Align blocks to page-size (#43689)

2026-06-03 14:25:57 +03:00

metrics

[Metrics] Exclude KV transfer tokens from iteration_tokens_total (#43346)

2026-05-29 19:56:44 +00:00

pool

[Misc] Added missing return type annotations to improve mypy and IDE tooling (#43383)

2026-05-23 13:28:22 +08:00

sample

[Minor] Remove FlashInfer version check in topk_topp_sampler (#44442)

2026-06-03 21:06:00 +00:00

simple_kv_offload

[Core][Refactor]: thread scheduler_block_size into KVCacheManager and KVCacheCoordinator (#44165)

2026-06-02 01:14:44 -07:00

spec_decode

[Bugfix] Fix Gemma4 MTP block_table batch_size mismatch under concurrent load (#43982)

2026-06-03 17:11:10 -07:00

structured_output

[Bug][Structured Outputs] Fix bug that leads to unconstrained generations with structural tags (#42452)

2026-05-20 07:08:58 -07:00

worker

[Core] Freeze garbage collector in workers after model initialization (#44363)

2026-06-04 08:39:04 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

cudagraph_dispatcher.py

[Experimental] Breakable CUDA graph (#42304)

2026-05-16 22:04:12 +08:00

kv_cache_interface.py

[DSv4] Adding TRTLLM gen attention kernel (#43827)

2026-06-04 07:35:09 -07:00

kv_cache_spec_registry.py

[KVCache] Support Pluggable KVCacheSpec (#37505)

2026-06-03 09:05:16 -07:00

outputs.py

[Core] Cleanup KVConnector handling with PP + fix MRV2 (#43732)

2026-05-28 13:12:03 -07:00

request.py

[ModelRunnerV2] Avoid pipeline parallel bubbles (#42187)

2026-06-02 14:02:01 -07:00

serial_utils.py

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

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

utils.py

[Frontend] Consolidate online serving utils. (#44479)

2026-06-04 06:49:31 +00:00