Juan Pérez de Algaba 8a5cf1ccd6 [Security] Fix remote DoS via invalid recovered token reinjection (#44744) ...

Signed-off-by: jperezde <jperezde@redhat.com>

2026-06-10 02:31:43 -07:00

..

attention

[Core][Model] Gemma4: Unified FA4 for all layers + FlashAttention mm_prefix support (#42175)

2026-06-09 17:45:39 -07:00

core

[Bugfix]: Fix assertion in MambaManager.allocate_slots() (#39562)

2026-06-08 00:34:37 -04:00

engine

[Core][Engine] allow DP ray placement groups to be set on specific nodes (#44669)

2026-06-05 20:07:47 +00:00

executor

[KVConnector][1/N] PP-aware handshake aggregation and intermediate-PP output plumbing (#43720)

2026-06-04 22:04:19 -07:00

kv_offload

[XPU] Support cpu kv offloading and tiering offloading on XPU platform (#36423)

2026-06-07 09:59:28 +08:00

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

[Security] Fix remote DoS via invalid recovered token reinjection (#44744)

2026-06-10 02:31:43 -07:00

simple_kv_offload

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

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

spec_decode

[SpecDecode] Reduce TP communication for large-vocab draft models speculative decoding (#39419)

2026-06-10 07:59:24 +00:00

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][Model] Gemma4: Unified FA4 for all layers + FlashAttention mm_prefix support (#42175)

2026-06-09 17:45:39 -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

[Misc] usage_stats: report more engine, spec-decode, and EP config (#44595)

2026-06-08 15:20:00 -07:00