Release Checks

Workflow runs for Release Checks

• [None][fix] Release GIL around cudaLaunchHostFunc to fix guided-decoding host-func deadlock

  failed:
  Release Checks#63:Pull request#17openedbysopwg612
  fix/guided-hostfunc-gil-deadlock-deep-main-rc16

  Jul 1, 20261m 24s
  More actions for workflow run 63

• [None][fix] PyExecutor: non-fatal KV-cache block-pool exhaustion guard

  failed:
  Release Checks#62:Pull request#16openedbyThachnh
  fix/kv-exhaustion-nonfatal-guard

  Jun 30, 20261m 27s
  More actions for workflow run 62

• used a wrapper on dynamo local kv indexer in the engine pod for snapshotting + replay

  failed:
  Release Checks#61:Pull request#14synchronizebymohammed-deepinfra
  mohammed/kv-local-indexer-worker

  Jun 30, 20261m 23s
  More actions for workflow run 61

• used a wrapper on dynamo local kv indexer in the engine pod for snapshotting + replay

  failed:
  Release Checks#60:Pull request#14synchronizebymohammed-deepinfra
  mohammed/kv-local-indexer-worker

  Jun 30, 20261m 34s
  More actions for workflow run 60

• used a wrapper on dynamo local kv indexer in the engine pod for snapshotting + replay

  failed:
  Release Checks#59:Pull request#14synchronizebymohammed-deepinfra
  mohammed/kv-local-indexer-worker

  Jun 30, 20261m 26s
  More actions for workflow run 59

• used a wrapper on dynamo local kv indexer in the engine pod for snapshotting + replay

  failed:
  Release Checks#58:Pull request#14synchronizebymohammed-deepinfra
  mohammed/kv-local-indexer-worker

  Jun 30, 20261m 24s
  More actions for workflow run 58

• used a wrapper on dynamo local kv indexer in the engine pod for snapshotting + replay

  failed:
  Release Checks#57:Pull request#14synchronizebymohammed-deepinfra
  mohammed/kv-local-indexer-worker

  Jun 30, 20261m 23s
  More actions for workflow run 57

• used a wrapper on dynamo local kv indexer in the engine pod for snapshotting + replay

  failed:
  Release Checks#56:Pull request#14synchronizebymohammed-deepinfra
  mohammed/kv-local-indexer-worker

  Jun 29, 20261m 22s
  More actions for workflow run 56

• [None][feat] KV-cache transfer/staging between two TRT-LLM instances

  failed:
  Release Checks#55:Pull request#15openedbynafis271
  deep-main-v1.3.0rc19-kv-transfer

  Jun 29, 20261m 32s
  More actions for workflow run 55

• used a wrapper on dynamo local kv indexer in the engine pod for snapshotting + replay

  failed:
  Release Checks#54:Pull request#14openedbymohammed-deepinfra
  mohammed/kv-local-indexer-worker

  Jun 27, 20261m 28s
  More actions for workflow run 54

• snapshotting for indexers

  failed:
  Release Checks#53:Pull request#13openedbymohammed-deepinfra
  kv-indexer-snapshot

  Jun 26, 20261m 17s
  More actions for workflow run 53

• [None][fix] fix for rejection sampling warmup crash (upstream Pr #15233)

  failed:
  Release Checks#52:Pull request#12openedbychungen28
  chungen/rej-sampling-fix

  Jun 25, 20262m 10s
  More actions for workflow run 52

• small patch for replay endpoing send watermark

  failed:
  Release Checks#51:Pull request#11openedbymohammed-deepinfra
  mohammed/wip-kv-cache

  Jun 23, 20261m 42s
  More actions for workflow run 51

• [None][fix] spec-decode NaN guard (~isnan, not isfinite) + draft_len_schedule CUDA-graph crash

  failed:
  Release Checks#50:Pull request#10openedbysopwg612
  fix/spec-guard-isnan-draftlen-deep-main-rc16

  Jun 17, 20261m 42s
  More actions for workflow run 50

• [None][fix] spec-decode NaN guard (~isnan, not isfinite) + draft_len_schedule CUDA-graph crash

  failed:
  Release Checks#49:Pull request#9openedbysopwg612
  fix/spec-guard-isnan-draftlen-priority-rc16

  Jun 17, 20261m 22s
  More actions for workflow run 49

• [None][feat] Add ZMQ KV-cache event tee with gap replay

  failed:
  Release Checks#48:Pull request#8synchronizebymohammed-deepinfra
  mohammed/wip-kv-cache

  Jun 17, 20261m 52s
  More actions for workflow run 48

• [None][feat] Add ZMQ KV-cache event tee with gap replay

  failed:
  Release Checks#47:Pull request#8synchronizebymohammed-deepinfra
  mohammed/wip-kv-cache

  Jun 16, 20261m 28s
  More actions for workflow run 47

• [None][feat] Add ZMQ KV-cache event tee with gap replay

  failed:
  Release Checks#46:Pull request#8openedbymohammed-deepinfra
  mohammed/wip-kv-cache

  Jun 15, 20261m 22s
  More actions for workflow run 46

• [None][feat] Add per-request priority support to OpenAI chat/completions

  failed:
  Release Checks#45:Pull request#7openedbysopwg612
  priority-request-v1.3.0rc16

  Jun 11, 20261m 22s
  More actions for workflow run 45

• [None][feat] Parallel prefault and THP knob for KV cache manager v2 host pools

  failed:
  Release Checks#44:Pull request#6synchronizebynafis271
  hostmem-prefault-thp-knobs

  Jun 11, 20261m 45s
  More actions for workflow run 44

• [None][feat] Parallel prefault and THP knob for KV cache manager v2 host pools

  failed:
  Release Checks#43:Pull request#6openedbynafis271
  hostmem-prefault-thp-knobs

  Jun 11, 20261m 27s
  More actions for workflow run 43

• [None][feat] Add per-request stream_interval_ms support

  failed:
  Release Checks#42:Pull request#5synchronizebyquan-deepinfra
  interval-ms

  Apr 7, 202616m 24s
  More actions for workflow run 42

• [None][feat] Add per-request stream_interval_ms support

  cancelled:
  Release Checks#41:Pull request#5synchronizebyquan-deepinfra
  interval-ms

  Apr 7, 202613m 30s
  More actions for workflow run 41

• [None][feat] Add per-request stream_interval_ms support

  cancelled:
  Release Checks#40:Pull request#5synchronizebyquan-deepinfra
  interval-ms

  Apr 7, 20264m 20s
  More actions for workflow run 40

• [None][feat] Add per-request stream_interval_ms support

  failed:
  Release Checks#39:Pull request#5synchronizebyquan-deepinfra
  interval-ms

  Apr 5, 202613m 34s
  More actions for workflow run 39