Bot-Command

Workflow runs for Bot-Command

• [TRTLLM-15765][refactor] Remove the ModelEngine ABC and settle the executor interface

  skipped:
  Bot-Command#274024:Issue comment#20996 (comment)createdbytensorrt-cicd
  Oct 26, 20262s
  More actions for workflow run 274024

• [TRTLLM-15765][refactor] Remove the ModelEngine ABC and settle the executor interface

  skipped:
  Bot-Command#274023:Issue comment#20996 (comment)createdbycoderabbitai[bot]Bot
  Oct 26, 20261s
  More actions for workflow run 274023

• [None][fix] Kimi K3 attn_res persistent fused kernel: 64-bit candidate offsets above the int range

  skipped:
  Bot-Command#274022:Issue comment#21011 (comment)createdbyYeonguChoe
  Oct 26, 20268s
  More actions for workflow run 274022

• [TRTLLM-15765][refactor] Remove the ModelEngine ABC and settle the executor interface

  skipped:
  Bot-Command#274021:Issue comment#20996 (comment)createdbylori-ren
  Oct 26, 20261s
  More actions for workflow run 274021

• [None][test] Add coverage for Qwen4ExpForConditionalGeneration

  skipped:
  Bot-Command#274020:Issue comment#21015 (comment)createdbytensorrt-cicd
  Oct 26, 20261s
  More actions for workflow run 274020

• [None][feat] Consolidate Kimi K3 native modeling work into main (#19990, #19991)

  skipped:
  Bot-Command#274019:Issue comment#20893 (comment)createdbyvsabavat
  Oct 26, 20261s
  More actions for workflow run 274019

• [None][chore] Remove the Python KV bounce buffer; kv_cache_bounce_size_mb selects the C++ agent bounce

  skipped:
  Bot-Command#274018:Issue comment#20049 (comment)createdbytensorrt-cicd
  Oct 26, 20261s
  More actions for workflow run 274018

• [None][fix] DeepSeek DSML tool parsers: the layout newlines around tool calls are not content

  skipped:
  Bot-Command#274017:Issue comment#20873 (comment)createdbytensorrt-cicd
  Oct 26, 20261s
  More actions for workflow run 274017

• [None][fix] DeepSeek DSML tool parsers: the layout newlines around tool calls are not content

  skipped:
  Bot-Command#274016:Issue comment#20873 (comment)createdbytensorrt-cicd
  Oct 26, 20261s
  More actions for workflow run 274016

• [TRTLLM-16722][feat] Dflash Unified KVCache

  skipped:
  Bot-Command#274015:Issue comment#20486 (comment)createdbytensorrt-cicd
  Oct 26, 20261s
  More actions for workflow run 274015

• [TRTLLM-17005][refactor] Component-local C++ Tests (Part 3a)

  skipped:
  Bot-Command#274014:Issue comment#21022 (comment)createdbytensorrt-cicd
  Oct 26, 20261s
  More actions for workflow run 274014

• [None][feat] Anthropic Messages: carry the engine request id in the message id

  skipped:
  Bot-Command#274013:Issue comment#20936 (comment)createdbycoderabbitai[bot]Bot
  Oct 26, 20262s
  More actions for workflow run 274013

• [None][feat] Anthropic Messages: carry the engine request id in the message id

  skipped:
  Bot-Command#274012:Issue comment#20936 (comment)createdbyJunyiXu-nv
  Oct 26, 20267s
  More actions for workflow run 274012

• [None][fix] DeepSeek DSML tool parsers: the layout newlines around tool calls are not content

  skipped:
  Bot-Command#274011:Issue comment#20873 (comment)createdbyJunyiXu-nv
  Oct 26, 20262s
  More actions for workflow run 274011

• [TRTLLM-15764][refactor] Split PyTorchModelEngine construction into named phases

  skipped:
  Bot-Command#274010:Issue comment#20851 (comment)createdbytensorrt-cicd
  Oct 26, 20266s
  More actions for workflow run 274010

• [None][feat] Kimi K3: support NVFP4 KV cache (FP4 MLA) with the hybrid KV cache manager

  skipped:
  Bot-Command#274009:Issue comment#20888 (comment)createdbytensorrt-cicd
  Oct 26, 2026Skipped
  More actions for workflow run 274009

• [https://nvbugs/6949270][fix] Size the Wan2.2-I2V serve test start budget to a cold checkpoint read

  skipped:
  Bot-Command#274008:Issue comment#20827 (comment)createdbytaianz-nv
  Oct 26, 2026Skipped
  More actions for workflow run 274008

• [None][feat] Kimi K3: support NVFP4 KV cache (FP4 MLA) with the hybrid KV cache manager

  skipped:
  Bot-Command#274007:Issue comment#20888 (comment)createdbyreasonsolo
  Oct 26, 20261s
  More actions for workflow run 274007

• [None][test] Remove 75 closed-bug waive entries for main

  skipped:
  Bot-Command#274006:Issue comment#20964 (comment)createdbytensorrt-cicd
  Oct 26, 20261s
  More actions for workflow run 274006

• [TRTLLM-17328][chore] Remove quantized FlashInfer TRTLLM-Gen MoE leaves and FlashInfer two-sided alltoall

  skipped:
  Bot-Command#274005:Issue comment#21013 (comment)createdbytensorrt-cicd
  Oct 26, 20269s
  More actions for workflow run 274005

• [TRTLLM-17005][refactor] Component-local C++ Tests (Part 3a)

  skipped:
  Bot-Command#274004:Issue comment#21022 (comment)createdbytensorrt-cicd
  Oct 26, 20261s
  More actions for workflow run 274004

• [https://nvbugs/6913452][fix] Fix flaky SF check in CuTe DSL gather act-fusion relu2 test

  skipped:
  Bot-Command#274003:Issue comment#20799 (comment)createdbytensorrt-cicd
  Oct 26, 20262s
  More actions for workflow run 274003

• [TRTLLM-17328][chore] Remove quantized FlashInfer TRTLLM-Gen MoE leaves and FlashInfer two-sided alltoall

  skipped:
  Bot-Command#274002:Issue comment#21013 (comment)createdbytensorrt-cicd
  Oct 26, 202610s
  More actions for workflow run 274002

• [TRTLLM-17229][feat] Extend the mixed-precision KV cache to speculative decoding and the sparse MLA backends

  skipped:
  Bot-Command#274001:Issue comment#21021 (comment)createdbycoderabbitai[bot]Bot
  Oct 26, 202610s
  More actions for workflow run 274001

• [None][feat] Kimi K3: support NVFP4 KV cache (FP4 MLA) with the hybrid KV cache manager

  skipped:
  Bot-Command#274000:Issue comment#20888 (comment)createdbytensorrt-cicd
  Oct 26, 20261s
  More actions for workflow run 274000