Commits · 1caf66591ade1166fd2fefb2e311ddcf09ee5120 · OpenDAS / dynamo

06 Apr, 2026 2 commits

feat(kvbm): KVBM MLA support optimization (#7015) · 1caf6659

Aniket Kulkarni authored Apr 06, 2026


Signed-off-by: aknvda <anikkulkarni@nvidia.com>
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: jthomson04 <jwillthomson19@gmail.com>

1caf6659

chore: Missed cleanup, delete batch mode (#7873) · ac60a0e1
Graham King authored Apr 06, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
ac60a0e1

04 Apr, 2026 4 commits
- fix(kv-router): migrate raw zmq paths to libzmq and refresh lockfiles (#7871) · f849e1a6
  Yan Ru Pei authored Apr 04, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  f849e1a6
- fix(ci): include benchmarks in test image (#7888) · bfc59cd2
  Yan Ru Pei authored Apr 04, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  bfc59cd2
- fix(frontend): Kimi tokenizer fix - use absolute token ID in tiktoken reserved... · 9ad38639
  Biswa Panda authored Apr 03, 2026
```
fix(frontend): Kimi tokenizer fix - use absolute token ID in tiktoken reserved token fallback names (#7886)
```
  9ad38639
- fix: honor per-node GPU topology in DGD builder (DYN-2544) (#7868) · d94c2ea2
  Hongkuan Zhou authored Apr 03, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  d94c2ea2
03 Apr, 2026 19 commits
- chore: remove vLLM patches for agg embedding cache (#7799) · eac5e463
  Qi Wang authored Apr 03, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  eac5e463
- refactor: switch trtllm config modifier to --trtllm.* dynamic CLI flags (#7884) · a72bd22d
  Hongkuan Zhou authored Apr 03, 2026
  
  a72bd22d
- docs(mm-router): remove vLLM patch requirement for MM router worker (#7878) · ddaf0fb5
  Kris Hung authored Apr 03, 2026
  
  ddaf0fb5
- feat: multimodal request_rate based sweep (#7363) · 5c461d61
  Qi Wang authored Apr 03, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  5c461d61
- fix(bench): replay mooncake events offline (#7876) · c08034eb
  Yan Ru Pei authored Apr 03, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  c08034eb
- fix(kv-router): default to compressed concurrent tree (#7874) · 04e05f8c
  Yan Ru Pei authored Apr 03, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  04e05f8c
- feat: add owner references to DGDR-created ConfigMaps (#7782) · a98b4d1f
  hhzhang16 authored Apr 03, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  a98b4d1f
- refactor(snapshot): add manifest-based snapshotctl flow and shared workload builders (#7671) · 43e810a4
  Schwinn Saereesitthipitak authored Apr 03, 2026
```
Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
```
  43e810a4
- feat(frontend): forward multimodal URLs from Python preprocessors to backend (#7837) · 23144df5
  Neal Vaidya authored Apr 03, 2026
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  23144df5
- fix: reuse elapsed duration in InflightGuard::Drop [DIS-1643] (#7869) · 63915ef5
  Neelay Shah authored Apr 03, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  63915ef5
- fix(kv-router): clean up watermarks on worker deregister (#7863) · 4cf04338
  doujiang24 authored Apr 04, 2026
```
Signed-off-by: zhudejiang.pt <zhudejiang.pt@antgroup.com>
```
  4cf04338
- chore(multimodal): Cleanup multimodal docs and consolidate launch scripts (#7845) · dacb2980
  Ryan McCormick authored Apr 03, 2026
  
  dacb2980
- build(sglang): slim runtime image (#7850) · 2075eb67
  Alec authored Apr 03, 2026
  
  2075eb67
- fix: minor fixes (test parser, verbose flags, and adding comments to clarify gpu_1 usage) (#7841) · 5bd30719
  Keiven C authored Apr 03, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  5bd30719
- chore: Add debug statements to GAIE test (#7846) · 6e202956
  atchernych authored Apr 03, 2026
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  6e202956
- ci: remove -amd64 suffix from GAIE deploy test image tag (#7848) · 67f732fd
  Tushar Sharma authored Apr 03, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  67f732fd
- chore(replay-optimize): quiet the sweep chatter (#7838) · 38b99369
  Yan Ru Pei authored Apr 02, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  38b99369
- feat: request lifecycle logging + metrics capture [DIS-1643] (#7840) · 679d9f14
  Neelay Shah authored Apr 02, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  679d9f14
- build(container): remove planner deps from non-planner images [DYN-2540] (#7748) · 59d32d25
  Alec authored Apr 02, 2026
  
  59d32d25
02 Apr, 2026 15 commits
- chore: Make mm router vllm tests to pre_merge (#7736) · 492acd03
  zhongdaor-nv authored Apr 02, 2026
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
```
  492acd03
- refactor(vLLM): Move video support from example to backend (#7663) · 4791aaaa
  Ryan McCormick authored Apr 02, 2026
  
  4791aaaa
- feat: enable KVBM Disk allocation support different storage types (#7839) · 234a89c0
  Ziqi Fan authored Apr 02, 2026
```
Signed-off-by: Ziqi Fan <ziqif@nvidia.com>
```
  234a89c0
- refactor: unify on_response, rename request_id fields, deprecate x-dynamo-request-id (#7834) · c376655f
  Neelay Shah authored Apr 02, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  c376655f
- feat: enable DP for GAIE (#7741) · 2b906504
  atchernych authored Apr 02, 2026
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  2b906504
- feat: use CUDA_VISIBLE_DEVICES instead of --gpus, multi-line GPU status output (#7825) · bcab0304
  Keiven C authored Apr 02, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  bcab0304
- refactor(kv-router): tidy indexer test query helpers (#7801) · 1f10ba55
  Yan Ru Pei authored Apr 02, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  1f10ba55
- fix: use unique DGD name following DGDR (#7778) · 3d8e85e2
  hhzhang16 authored Apr 02, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  3d8e85e2
- feat: trace infrastructure — spans + request ID propagation [DIS-1643] (#7733) · 13058cbd
  Neelay Shah authored Apr 02, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  13058cbd
- refactor: move omni post-processing to dedicated formatters / processors (#7746) · 658b0d5a
  Ayush Agarwal authored Apr 02, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  658b0d5a
- Rename stale max_vram_gib marker to profiled_vram_gib (#7829) · 12b4dec5
  Keiven C authored Apr 02, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  12b4dec5
- feat: support chat_template.json as a prompt formatter artifact (#7785) · 06a24503
  Neal Vaidya authored Apr 02, 2026
```
Closes https://github.com/ai-dynamo/dynamo/issues/7737
```
  06a24503
- fix: support OpenAI content arrays in DeepSeek V3.2 prompt rendering (#6321) · 52a3ca94
  Vladislav Nosivskoy authored Apr 02, 2026
```
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
```
  52a3ca94
- fix: Replace hardcoded SA suffix matching with config-driven allow-list for... · a96d9c51
  Julien Mancuso authored Apr 02, 2026
```
fix: Replace hardcoded SA suffix matching with config-driven allow-list for DGD replicas webhook (#7656) (#7682)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  a96d9c51
- feat: GPU-parallel test runner with VRAM-aware scheduling (#7560) · 6dc85fbc
  Keiven C authored Apr 02, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  6dc85fbc