Commits · 5802db87c9bf7a226ec132405b0de4c8b20ccbfc · OpenDAS / dynamo · GitLab

08 Apr, 2026 3 commits
- feat(sglang): add logprob passthrough in decode handler (#6837) · 5802db87
  William Arnold authored Apr 07, 2026
```
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  5802db87
- fix(migration): disable migration for guided-decoding requests (#7930) · c53ef736
  MatejKosec authored Apr 07, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  c53ef736
- fix(nixl): fix iteration_count debug logging in _wait_for_completion_ (#7966) · 88966f02
  MatejKosec authored Apr 07, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  88966f02
07 Apr, 2026 26 commits
- chore(ci): add xpu label to PR labeler (#7967) · 5841deda
  Ryan McCormick authored Apr 07, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  5841deda
- feat: add I2I (image-to-image) support for SGLang diffusion backend (#7870) · 225dad4d
  KrishnanPrash authored Apr 07, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  225dad4d
- fix: flatten imported dashboard results for Allure 3 scanner (#7963) · ba2185a0
  Dmitry Tokarev authored Apr 07, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  ba2185a0
- fix(operator): use ConfigMap for vLLM multinode wait-for-leader script (#7954) · 317b9614
  Julien Mancuso authored Apr 07, 2026
  
  317b9614
- refactor: split build_gpu_mem_args into engine-specific functions (#7916) · 4cdc49c2
  Keiven C authored Apr 07, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  4cdc49c2
- feat(sglang): add video input support for aggregated serving (#7941) · b1c18bb1
  Zhuangcheng Gu authored Apr 07, 2026
```
Signed-off-by: Chokoyo <40918450+Chokoyo@users.noreply.github.com>
```
  b1c18bb1
- test: e2e JSONL log verification for request tracing (#7817) · 73f8557a
  Neelay Shah authored Apr 07, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  73f8557a
- fix(trtllm): populate disagg_request_id for PYTHON transceiver (#7604) · 122777c8
  Yifan Jiang authored Apr 07, 2026
```
Signed-off-by: Yifan Jiang <19356972+yifjiang@users.noreply.github.com>
```
  122777c8
- chore(kv-router): tighten indexer cleanup helpers (#7945) · 22da711f
  Yan Ru Pei authored Apr 07, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  22da711f
- fix(snapshot): add checkpoint and restore timing summaries (#7949) · 5a3fa1fd
  Schwinn Saereesitthipitak authored Apr 07, 2026
```
Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
```
  5a3fa1fd
- fix: call inflight.mark_error() in media handler error paths (#7917) · a27475de
  MatejKosec authored Apr 07, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  a27475de
- feat: add Allure test dashboard on GitHub Pages (#6903) · e24b25f8
  Dmitry Tokarev authored Apr 07, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  e24b25f8
- feat(frontend): allowing passing vllm chat processor specific flags in frontend (#7896) · c021814f
  Biswa Panda authored Apr 07, 2026
  
  c021814f
- fix(operator): handle spec-less resources (ConfigMaps, Secrets, etc.) in SyncResource (#7953) · 942070c2
  Julien Mancuso authored Apr 07, 2026
  
  942070c2
- fix: broken vLLM nightly gpu_2 test and vLLM API compatibility errors (#7865) · 3ad7b7c8
  Keiven C authored Apr 07, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  3ad7b7c8
- fix: remove sanity check from CI; it is only meant for developers to quickly... · 0a4b5d42
  Keiven C authored Apr 07, 2026
```
fix: remove sanity check from CI; it is only meant for developers to quickly check for correct compilation/inference dependencies (#7892)
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Ran Rubin <ranrubin@gmail.com>
```
  0a4b5d42
- fix(sglang): make prefill warmup failure fatal (#7944) · eb675ae3
  Neelay Shah authored Apr 07, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  eb675ae3
- chore: bump vLLM to 0.19.0 (#7894) · d5803cbe
  Alec authored Apr 07, 2026
  
  d5803cbe
- feat: deprecated namespace-restricted mode (#7934) · ad3a46a6
  Julien Mancuso authored Apr 07, 2026
  
  ad3a46a6
- feat(tests): add pytest markers to tests not picked up by CI (#7936) · 0078e283
  Keiven C authored Apr 07, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  0078e283
- fix(mocker): restore disagg cache reuse accounting (#7938) · d42ff092
  Yan Ru Pei authored Apr 06, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  d42ff092
- feat: Request Rejection Frontend metrics (#7644) · 3205e7db
  Jacky authored Apr 06, 2026
```
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
```
  3205e7db
- fix(parsers): parallel XML/JSON tool calls no longer drop N-1 of N calls (#7914) · 91700375
  MatejKosec authored Apr 06, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  91700375
- feat: add a few TRT-LLM example support for GPU-parallel test execution (#7880) · ad2205eb
  Keiven C authored Apr 06, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  ad2205eb
- fix(kv-router): correct decode-worker scoring for unregistered workers in selector (#7919) · 2af062ec
  MatejKosec authored Apr 06, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  2af062ec
- chore: Add make targets for tooling binaries in operator (#7609) · 189d2178
  Jonathan Tong authored Apr 06, 2026
```
Signed-off-by: Jont828 <jt572@cornell.edu>
```
  189d2178
06 Apr, 2026 11 commits
- feat: deprecated namespace-restricted mode (#7907) · ae53d7c4
  Julien Mancuso authored Apr 06, 2026
  
  ae53d7c4
- feat: add templates and skills for issue-based DEPs (#7765) · 46070b36
  Neelay Shah authored Apr 06, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Dan Gil <dagil@nvidia.com>
```
  46070b36
- perf(multimodal): strip inline base64 from TCP transport in frontend decoding (#7895) · 6b8545fc
  Qi Wang authored Apr 06, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  6b8545fc
- fix(vllm): eliminate redundant image re-download on decode worker in disagg multimodal (#7827) · da670d44
  Qi Wang authored Apr 06, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  da670d44
- fix: latch busy load until both cool off (#7912) · ffe20629
  Yan Ru Pei authored Apr 06, 2026
```
Signed-off-by: AmeenP <ameenp360@gmail.com>
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: AmeenP <ameenp360@gmail.com>
```
  ffe20629
- chore(replay): refactor offline components into cleaner lanes (#7866) · 95a750f4
  Yan Ru Pei authored Apr 06, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  95a750f4
- chore(multimodal): add notes/warn about encoder disagg not supporting video_url yet (#7890) · 210bbf5d
  Ryan McCormick authored Apr 06, 2026
  
  210bbf5d
- feat(mocker): add MoE parallelism params to AIC perf model (#7856) · 3292ed1b
  Yongming Ding authored Apr 06, 2026
```
Signed-off-by: Yongming Ding <yongmingd@nvidia.com>
```
  3292ed1b
- fix(sglang): use incremental streaming output for completions (#7752) · b2cafb7f
  weireweire authored Apr 07, 2026
```
Signed-off-by: Weiliangl User <weiliangl@login-node.hosted.internal>
Co-authored-by: Weiliangl User <weiliangl@login-node.hosted.internal>
```
  b2cafb7f
- fix: Handle anyOf/oneOf parameter schemas in Qwen3Coder tool parser (#7847) · 0ba80f6a
  Neal Vaidya authored Apr 06, 2026
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
```
  0ba80f6a
- fix: Fix multinode gang scheduling by setting MinAvailable to replica count on cliques (#7905) · 6e0d62d7
  Julien Mancuso authored Apr 06, 2026
  
  6e0d62d7