Ajay AnuboluandMatthew Bonanni bf5149b516 [Bugfix] Fix FlashMLA sparse accuracy with topk_length and zero-init padding (#36616) ...

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

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

..

attention

[Bugfix] Fix FlashMLA sparse accuracy with topk_length and zero-init padding (#36616)

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

core

[Bugfix] Defer block freeing until in-flight steps finish under async scheduling + PD KV consumer (#45357)

2026-06-15 21:36:09 +00:00

engine

[Core][AMD] Propagate shutdown timeout to MultiprocExecutor (#43154)

2026-06-12 15:13:31 -05:00

executor

[Core] Simplify MRV2 async output handling (#45442)

2026-06-13 18:15:36 -07:00

kv_offload

[KV Offloading] Implement reset_cache for TieringOffloadingManager (#44541)

2026-06-15 18:42:53 +00:00

metrics

[Migration] Migrate GGUF quantization support to plugin (#39612)

2026-06-12 12:02:21 -07:00

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

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

structured_output

[Security] Add timeout guard for regex compilation in structured outp… (#45118)

2026-06-13 09:52:56 +00:00

worker

[MM][Perf][CG] Support dual-path ViT full CUDA graph for DeepSeek-OCR (#43586)

2026-06-16 04:35:20 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

cudagraph_dispatcher.py

[Model] Add DiffusionGemma Support (#45163)

2026-06-11 22:17:35 -07:00

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

[Bugfix] Defer block freeing until in-flight steps finish under async scheduling + PD KV consumer (#45357)

2026-06-15 21:36:09 +00:00

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