All workflows

Workflow runs

• GPU Perf Weekly

  completed successfully:
  GPU Perf Weekly#6:Scheduled
  main

  Nov 8, 20261h 5m 42s
  More actions for workflow run 6

• fix(allocator): forecast capacity from allocatable page IDs (#617)

  completed successfully:
  CPU Tests#799:Commitea200f7pushedbyshipiyouniao
  main

  Nov 8, 20265m 32s
  More actions for workflow run 799

• fix(allocator): forecast capacity from allocatable page IDs (#617)

  completed successfully:
  Pre-commit CI#2567:Commitea200f7pushedbyshipiyouniao
  main

  Nov 8, 202638s
  More actions for workflow run 2567

• fix(allocator): forecast capacity from allocatable page IDs

  completed successfully:
  Pre-commit CI#2566:Pull request#617synchronizebygoogs1025
  googs1025:fix/page-capacity-forecast

  Nov 8, 20261m 35s
  More actions for workflow run 2566

• fix(allocator): forecast capacity from allocatable page IDs

  completed successfully:
  CPU Tests#798:Pull request#617synchronizebygoogs1025
  googs1025:fix/page-capacity-forecast

  Nov 8, 20265m 36s
  More actions for workflow run 798

• fix(sglang): keep MLA block IDs inside the native writer bound

  completed successfully:
  CPU Tests#797:Pull request#619openedbyrishabhsinha17
  rishabhsinha17:fix/mla-max-block-id

  Nov 8, 20265m 39s
  More actions for workflow run 797

• fix(sglang): keep MLA block IDs inside the native writer bound

  completed successfully:
  Pre-commit CI#2565:Pull request#619openedbyrishabhsinha17
  rishabhsinha17:fix/mla-max-block-id

  Nov 8, 20261m 9s
  More actions for workflow run 2565

• Running Copilot Code Review

  completed successfully:
  Copilot#65:byCopilotAI
  main

  Nov 8, 20263m 35s

• fix(allocator): forecast capacity from allocatable page IDs

  completed successfully:
  CPU Tests#796:Pull request#617openedbygoogs1025
  googs1025:fix/page-capacity-forecast

  Nov 8, 20266m 13s
  More actions for workflow run 796

• fix(allocator): forecast capacity from allocatable page IDs

  completed successfully:
  Pre-commit CI#2564:Pull request#617openedbygoogs1025
  googs1025:fix/page-capacity-forecast

  Nov 8, 20261m 31s
  More actions for workflow run 2564

• feat(budget): keep a watermark of free memory for higher priorities (…

  completed successfully:
  Pre-commit CI#2563:Commitcfff54epushedbyRixinLiu
  main

  Nov 8, 20261m 13s
  More actions for workflow run 2563

• feat(budget): keep a watermark of free memory for higher priorities (…

  completed successfully:
  CPU Tests#795:Commitcfff54epushedbyRixinLiu
  main

  Nov 8, 20265m 56s
  More actions for workflow run 795

• feat(budget): keep a watermark of free memory for higher priorities

  skipped:
  GPU CI on pull request#146:Issue comment#608 (comment)createdbyRixinLiu
  Nov 8, 20261s
  More actions for workflow run 146

• fix(controller): forward upstream error status and body

  completed successfully:
  Pre-commit CI#2562:Pull request#616openedbyLumea-art
  Lumea-art:fix/controller-error-status

  Nov 8, 20261m 32s
  More actions for workflow run 2562

• fix(controller): forward upstream error status and body

  completed successfully:
  CPU Tests#794:Pull request#616openedbyLumea-art
  Lumea-art:fix/controller-error-status

  Nov 8, 20266m 14s
  More actions for workflow run 794

• GPU Correctness (weekly)

  completed successfully:
  GPU Correctness#6:Scheduled
  main

  Nov 7, 20261h 3m 18s
  More actions for workflow run 6

• fix(controller): avoid duplicate responses on stream failure (#615)

  completed successfully:
  Pre-commit CI#2561:Commitef581b0pushedbyshipiyouniao
  main

  Nov 7, 20261m 19s
  More actions for workflow run 2561

• fix(controller): avoid duplicate responses on stream failure (#615)

  completed successfully:
  CPU Tests#793:Commitef581b0pushedbyshipiyouniao
  main

  Nov 7, 20266m 30s
  More actions for workflow run 793

• Feature request: elastic backing for DSA caches in vLLM and SGLang (DeepSeek-V3.2, GLM-5)

  skipped:
  GPU CI on pull request#145:Issue comment#560 (comment)createdbyLumea-art
  Nov 7, 20261s
  More actions for workflow run 145

• fix(controller): stop sending a second response after a failed stream

  completed successfully:
  Pre-commit CI#2560:Pull request#615openedbyLumea-art
  Lumea-art:fix/controller-stream-double-response

  Nov 7, 20261m 6s
  More actions for workflow run 2560

• fix(controller): stop sending a second response after a failed stream

  completed successfully:
  CPU Tests#792:Pull request#615openedbyLumea-art
  Lumea-art:fix/controller-stream-double-response

  Nov 7, 20266m 17s
  More actions for workflow run 792

• Controller sends a second HTTP response after an upstream stream fails

  skipped:
  GPU CI on pull request#144:Issue comment#610 (comment)createdbyLumea-art
  Nov 7, 20261s
  More actions for workflow run 144

• feat(budget): keep a watermark of free memory for higher priorities

  skipped:
  GPU CI on pull request#143:Issue comment#608 (comment)createdbyrishabhsinha17
  Nov 7, 20261s
  More actions for workflow run 143

• ci: add the two-instance priority e2e case

  completed successfully:
  Pre-commit CI#2559:Pull request#613synchronizebyrishabhsinha17
  rishabhsinha17:ci/priority-e2e-case

  Nov 7, 20261m 26s
  More actions for workflow run 2559

• ci: add the two-instance priority e2e case

  completed successfully:
  CPU Tests#791:Pull request#613synchronizebyrishabhsinha17
  rishabhsinha17:ci/priority-e2e-case

  Nov 7, 20266m 11s
  More actions for workflow run 791