3 people 7d47cff933 [Bugfix][KV Offload] Fix swap_blocks_batch on the default stream (#46379) ...

Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <Itay.etelis@gmail.com>

2026-06-23 05:45:27 -07:00

..

attention

Enable DeepSeek V4 and GLM-5.1 on SM120 (#43477)

2026-06-22 11:54:14 -07:00

core

[v1][kvcache] Honor prefix-cache retention interval for Mamba/linear attention (#45845)

2026-06-22 19:51:11 -07:00

cudagraph

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

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

determinism

[Feature] Support batch invariant rms norm with residual (#42453)

2026-06-03 15:22:01 -04:00

distributed

[Core] Add prefill step cadence for better non-PD DP balancing (#44558)

2026-06-16 13:17:18 -07:00

e2e

[Hardware][AMD][CI] Fix Spec Decode Eagle test group (#46018)

2026-06-21 17:40:02 -05:00

ec_connector

[Docs] Fix broken local links (#42160)

2026-05-10 01:15:38 -07:00

engine

[Frontend] Split ServingRender into renderer and entrypoint. (#44285)

2026-06-23 11:19:09 +00:00

executor

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

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

kv_connector

[ROCm][P/D] Support MoRIIO heterogeneous TP fan-in (#46332)

2026-06-23 10:33:23 +00:00

kv_offload

[Bugfix][KV Offload] Fix swap_blocks_batch on the default stream (#46379)

2026-06-23 05:45:27 -07:00

logits_processors

[Core] Ensure memory is pinned prior to async h2d copy (#45424)

2026-06-20 20:02:24 -07:00

metrics

[V1][Metrics] Add MLA attention metrics for DeepSeek MFU estimation (#39457)

2026-06-12 14:28:40 +01:00

sample

[Bugfix][Model Runner V2] Preserve all allowed_token_ids in the logit bias kernel (#46245)

2026-06-23 07:01:13 +00:00

shutdown

[Bugfix][V1] Clean up compiled-model bytecode hooks on VllmRunner exit (#45195)

2026-06-16 20:31:17 -07:00

simple_kv_offload

[Bugfix][KVConnector] Fix SimpleCPUOffloadConnector GPU->CPU store race (#46278)

2026-06-22 13:08:47 -07:00

spec_decode

Enable DeepSeek V4 and GLM-5.1 on SM120 (#43477)

2026-06-22 11:54:14 -07:00

streaming_input

[Core] Ensure memory is pinned prior to async h2d copy (#45424)

2026-06-20 20:02:24 -07:00

structured_output

[Bugfix] Reject structured outputs for diffusion decoders with a clear error (#45468)

2026-06-13 12:04:01 -07:00

tracing

[Feature] OTEL tracing during loading (#31162)

2026-02-05 16:59:28 -08:00

worker

[Bugfix][Spec Decode] Fix EAGLE drafter multimodal encoder cache misses (#46315)

2026-06-22 18:14:02 +00:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

test_kv_cache_spec_registry.py

[KVCache] Support Pluggable KVCacheSpec (#37505)

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

test_oracle.py

[Docs] Clean up speculators docs (#34065)

2026-02-18 13:48:11 -08:00

test_outputs.py

[BugFix] Fix spec decoding max_tokens scheduling perf issue (#29542)

2025-11-28 20:52:23 +08:00

test_request.py

[Refactor] Rename WAITING_FOR_FSM to WAITING_FOR_STRUCTURED_OUTPUT_GRAMMAR (#38048)

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

test_serial_utils.py

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

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

test_tensor_ipc_queue.py

[Test] Refactor hard coded device string in test files under compile/quantization/models/model_executor folders (#38901)

2026-04-15 11:02:35 +08:00

utils.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00