Andreas Karatzas 61c1d098e5 [CI] Stabilize speculator memory teardown (#50284) ...

Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>

2026-07-30 18:42:55 +08:00

..

attention

[Test] Skip ROCm AITER MLA prefill tests on non-ROCm platforms (#49945)

2026-07-28 16:26:49 +08:00

core

[BugFix] Fix P/D preemption race condition (#50297)

2026-07-30 01:11:18 +00:00

cudagraph

[CI] Isolate cudagraph tests in child processes (#49510)

2026-07-23 17:16:19 +00:00

determinism

[Bugfix][Kernel] Fix batch invariance in RMSNorm kernels by pinning block size (#48391)

2026-07-28 22:24:02 +08:00

distributed

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

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

e2e

[CI] Stabilize speculator memory teardown (#50284)

2026-07-30 18:42:55 +08:00

ec_connector

[Test] Make EPD correctness tests configurable for XPU (#50110)

2026-07-29 07:47:48 +08:00

engine

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

executor

[Bugfix] Prevent stale multiproc RPC deadlines from becoming unbounded waits (#41357)

2026-07-29 16:41:34 -07:00

fault_tolerance

[Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)

2026-07-25 11:49:09 -04:00

kv_connector

[PD][Bugfix] Rebase KV lease deadlines onto worker clock (#50326)

2026-07-30 01:25:42 +00:00

kv_offload

[KV Offload] Move CPUOffloadingSpec onto SharedOffloadRegion (#50094)

2026-07-29 13:05:50 +03:00

logits_processors

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

metrics

[Refactor] Move iteration logging to the frontend (#46647)

2026-07-15 17:59:05 -07:00

sample

[Spec Decode][Perf] Replicate DSpark Markov head across TP ranks (#49731)

2026-07-29 11:43:51 -04:00

shutdown

[CI][ROCm] Fix AMD nightly distributed regressions (#50304)

2026-07-29 22:02:12 +00:00

simple_kv_offload

[Core] Add MRV2 virtual-batch PCP for MLA (#46570)

2026-07-19 02:53:15 +00:00

spec_decode

[BugFix] eagle draft max position embeddings (#49343)

2026-07-29 01:24:47 -07:00

streaming_input

[ModelRunner V2] Enable sequence pooling for embedding and classification models (#48791)

2026-07-29 06:30:45 -07:00

structured_output

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

tracing

[CI] Fix segfault in tracing test (#47299)

2026-07-01 14:00:37 +00:00

worker

[BugFix] Stop dummy runs from writing mamba state through stale block-table rows (#49757)

2026-07-29 01:09:41 +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

[MRV2][Spec Decode] Avoid rejection sampler OOM by chunking (#48630)

2026-07-23 18:13:13 +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

[Bugfix] Don't reuse engine core payload buffer while zmq is sending it (#50053)

2026-07-28 16:09:28 +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