Samu Tamminen c49497726b [ROCm][perf] Shuffle KV cache to use paged_attention_common (#32914) ...

Signed-off-by: Samu Tamminen <stammine@amd.com>
Co-authored-by: Tuukka Sarvi <tuukka.sarvi@amd.com>

2026-04-01 03:30:19 +00:00

..

attention

[ROCm][perf] Shuffle KV cache to use paged_attention_common (#32914)

2026-04-01 03:30:19 +00:00

core

[Feat][v1] Simple yet General CPU KV Cache Offloading (#37160)

2026-03-31 17:58:37 -07:00

engine

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

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

executor

replace cuda_device_count_stateless() to current_platform.device_count() (#37841)

2026-03-31 22:32:54 +08:00

kv_offload

[kv_offload+HMA] Fix num_blocks with different per-layer page sizes and improve assert message (#38554)

2026-03-31 06:00:40 +00:00

metrics

[Feat][v1] Simple yet General CPU KV Cache Offloading (#37160)

2026-03-31 17:58:37 -07:00

pool

[Perf] Remove redundant device copies for CPU-only pooling token IDs, 48.9% E2E throughput improvement (#38139)

2026-03-29 18:12:50 +00:00

sample

Generative Scoring (#34539)

2026-03-31 16:02:11 -07:00

simple_kv_offload

[Feat][v1] Simple yet General CPU KV Cache Offloading (#37160)

2026-03-31 17:58:37 -07:00

spec_decode

[ROCm][perf] fix Aiter sparse MLA with MTP>1 (#37887)

2026-03-31 19:22:23 -04:00

structured_output

[Bugfix] Add missing f-string prefix in xgrammar choices error message (#38162)

2026-03-26 21:43:03 +00:00

worker

Generative Scoring (#34539)

2026-03-31 16:02:11 -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

[BUGFIX][Mamba][Qwen3.5] Zero freed SSM cache blocks on GPU (#35219)

2026-03-10 03:32:20 -07:00

outputs.py

[KVConnector] Remove redundant method KVConnectorOutput::merge() (#38546)

2026-03-31 07:11:02 +03:00

request.py

[Refactor] Rename WAITING_FOR_FSM to WAITING_FOR_STRUCTURED_OUTPUT_GRAMMAR (#38048)

2026-03-25 11:41:44 -04:00

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