Douglas Lehrandganyi baf068d8be enable persistent mla for sparse mla backend (#41990) ...

Signed-off-by: ganyi <ygan@amd.com>
Signed-off-by: Douglas Lehr <Doug.Lehr@amd.com>
Co-authored-by: ganyi <ygan@amd.com>

2026-05-07 20:10:50 -07:00

..

attention

enable persistent mla for sparse mla backend (#41990)

2026-05-07 20:10:50 -07:00

core

[Core] Replace routing replay with device cache and async D2H pipeline (#39917)

2026-05-07 11:24:56 -07:00

engine

[Core] Replace routing replay with device cache and async D2H pipeline (#39917)

2026-05-07 11:24:56 -07:00

executor

[Core] Avoid using extra thread in UniProcExecutor (#40891)

2026-05-07 15:33:00 -07:00

kv_offload

[KV Offload] Return None from lookup() for in-flight blocks (#41795)

2026-05-06 17:31:21 +03:00

metrics

[Bugfix][Metrics] Fix RayPrometheusMetric.labels() returning shared labeled child (#40840)

2026-05-01 08:43:39 +01:00

pool

[Frontend] Re-enable running MaxSim on GPU (#38620)

2026-04-03 00:03:13 +08:00

sample

[XPU] use xpu topk topp sample kernel (#39285)

2026-05-05 18:05:17 +08:00

simple_kv_offload

[ROCm] Enable SimpleCPUOffloadConnector on ROCm (#40549)

2026-05-06 20:52:02 -07:00

spec_decode

[Spec Decode] Add Gemma4 MTP speculative decoding support (#41745)

2026-05-06 22:39:29 +08:00

structured_output

[Bugfix] Pass reasoning parser kwargs to structured output (#41199)

2026-04-30 23:38:02 -07:00

worker

[Perf][3/n] Eliminate GPU<->CPU syncs in attention impls (#41434)

2026-05-07 19:44:24 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

cudagraph_dispatcher.py

[Mypy] Fix mypy for vllm/config (#37808)

2026-03-23 14:33:59 +00:00

kv_cache_interface.py

Add nvfp4 kv cache support (#40177)

2026-05-01 04:55:16 +00:00

outputs.py

[Core] Replace routing replay with device cache and async D2H pipeline (#39917)

2026-05-07 11:24:56 -07:00

request.py

[Bugfix] Pass reasoning parser kwargs to structured output (#41199)

2026-04-30 23:38:02 -07:00

serial_utils.py

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

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

utils.py

[Refactor] Unify engine process monitoring in engine manager and add Ray backend support (#35862)

2026-03-30 10:16:09 -07:00