Commits · 91ddf4189b6c88963f57b50b416397da6759c511 · OpenDAS / dynamo

"docs/planner/sla_planner_quickstart.md" did not exist on "83e259a7ccf16d10c0bc175136f9092ed7c87ae3"

21 Jan, 2026 11 commits
- feat: v0 diffusion handler support (#5533) · 91ddf418
  Ayush Agarwal authored Jan 21, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  91ddf418
- test: Fixing kvbm tests/ adding concurrency test (#5474) · 224f63f5
  Olga Andreeva authored Jan 21, 2026
  
  224f63f5
- chore: [vLLM] Update the import paths from `vllm.entrypoints.openai` to align... · 199d11f5
  Shang Wang authored Jan 21, 2026
```
chore: [vLLM] Update the import paths from `vllm.entrypoints.openai` to align with vLLM latest `main` (#5447)
Signed-off-by: Shang Wang <shangw@nvidia.com>
Signed-off-by: Shang Wang <samshang.wang@mail.utoronto.ca>
Signed-off-by: Qidong Su <qidongs@nvidia.com>
Co-authored-by: Qidong Su <qidongs@nvidia.com>
```
  199d11f5
- chore: reduce verbosity during dynamo start (#5518) · e2b12517
  Biswa Panda authored Jan 21, 2026
  
  e2b12517
- feat: warmup dataset for planner load predictor (#5529) · b0959cfd
  Hongkuan Zhou authored Jan 21, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  b0959cfd
- feat: remove ser/deser in gather_multi_model_data (#5485) · 0f137de4
  milesial authored Jan 21, 2026
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  0f137de4
- feat: add PositionalLineageHash for hierarchical block tracking (DIS-1307) (#5522) · 34e58224
  Ryan Olson authored Jan 21, 2026
```
Signed-off-by: Ryan Olson <rolson@nvidia.com>
```
  34e58224
- chore: update attributions for vllm cuda13 container (#5436) (#5488) · 8877c46f
  Anant Sharma authored Jan 21, 2026
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  8877c46f
- fix: multi image bug for qwen ec connector (#5514) · 60700899
  Ayush Agarwal authored Jan 21, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  60700899
- fix: add test for long context kv store events and fix drop issue (#5499) · fdd2d15e
  blarson-b10 authored Jan 20, 2026
```
Signed-off-by: Brian Larson <brian.larson@baseten.co>
```
  fdd2d15e
- fix: restrict pod hash for worker/instance id to <2^53 (#5471) · ca023c0c
  Janelle Cai authored Jan 20, 2026
  
  ca023c0c
20 Jan, 2026 11 commits
- fix: ipv6 support for sglang disaggregation (#5521) · 9b8b35a8
  ishandhanani authored Jan 20, 2026
```
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  9b8b35a8
- refactor: clean up SGLang sleep/wake implementation (#5517) · 2e8c4447
  Schwinn Saereesitthipitak authored Jan 20, 2026
  
  2e8c4447
- fix(sglang): Fix YAML config parsing for store_true arguments (#5513) · 04cecda7
  ishandhanani authored Jan 20, 2026
  
  04cecda7
- feat(sglang): enforce stream_output=True for optimal streaming performance (#5510) · 748fee6b
  MatejKosec authored Jan 20, 2026
```
This ensures that only new tokens are returned by sglang which avoids the overhead from creating copies of the entire token sequences per each iteration. These copies can become a bottleneck particularly for long sequence lengths and large concurrency counts.
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  748fee6b
- fix: on a bad network day, uv timeout too easily when building dev/local-dev containers (#5511) · 7b639e76
  Keiven C authored Jan 20, 2026
```
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  7b639e76
- feat: Support Dynamo KVBM with TRTLLM Disagg (#3527) · bf19823d
  jthomson04 authored Jan 20, 2026
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
```
  bf19823d
- feat: SGLang release/resume_memory_occupation endpoints (#5207) · 0e0d6c16
  Schwinn Saereesitthipitak authored Jan 20, 2026
```
Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  0e0d6c16
- feat: Sleep/wake endpoints for vLLM runtime (#5339) · e2a0a4b5
  Schwinn Saereesitthipitak authored Jan 20, 2026
```
Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  e2a0a4b5
- feat: typing - Add py.typed support for typing (#4913) · fa66f654
  Michael Feil authored Jan 20, 2026
```
Signed-off-by: Michael Feil <63565275+michaelfeil@users.noreply.github.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>
```
  fa66f654
- test: Auto-start services for prompt_embed_tests.py (#5491) · e076f3a2
  Graham King authored Jan 20, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  e076f3a2
- feat: add endpoint instance registration/unregistration for sleep/wake (#5203) · d953f9d0
  Schwinn Saereesitthipitak authored Jan 20, 2026
```
Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  d953f9d0
18 Jan, 2026 3 commits
- chore: use u64 as router consumer id instead of uuid (#5478) · 602ce0ed
  Yan Ru Pei authored Jan 18, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  602ce0ed
- fix: remove store block recursion in favor of loop + don't try to detect loops (#5497) · d5befaab
  blarson-b10 authored Jan 17, 2026
```
Signed-off-by: Brian Larson <brian.larson@baseten.co>
```
  d5befaab
- feat: track output tokens / blocks in the Router (optional) (#5452) · 050906b5
  Yan Ru Pei authored Jan 18, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  050906b5
17 Jan, 2026 1 commit
- ci: use pull_request_target for labeler workflow (#5498) · 9c08a2aa
  Pavithra Vijayakrishnan authored Jan 17, 2026
```
Signed-off-by: pvijayakrish <pvijayakrish@nvidia.com>
```
  9c08a2aa
16 Jan, 2026 13 commits
- fix: make it clear what features are only available 0.8.1 and on (#5492) · a2c7d0f9
  hhzhang16 authored Jan 16, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  a2c7d0f9
- feat: add span event logging and fix trace context extraction (#5400) · 06939770
  Neelay Shah authored Jan 16, 2026
```
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  06939770
- feat: triton worker example (#4971) · 971c3069
  Neal Vaidya authored Jan 16, 2026
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
```
  971c3069
- chore: support for muliple MM requests for vLLM Encoder + Rust Based Preprocessor (#5463) · f9918f61
  Ayush Agarwal authored Jan 16, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  f9918f61
- chore: update attributions files for rust, go, vllm and trtllm (#5401) (#5484) · 50c54695
  Anant Sharma authored Jan 16, 2026
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  50c54695
- fix: add missing description to memory crate (#5483) · 3f4b3d4d
  Anant Sharma authored Jan 16, 2026
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  3f4b3d4d
- chore: SGlang attributions (#5455) · 4597fd95
  Dmitry Tokarev authored Jan 16, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Signed-off-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>
```
  4597fd95
- feat: sanity_check.py to simply print CUDA version (no check) (#5335) · f7ec1056
  Keiven C authored Jan 16, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  f7ec1056
- chore(bindings): Remove 'Backend' binding (#5458) · a6e73484
  Graham King authored Jan 16, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  a6e73484
- feat: SGLang aggregated multimodal support (#5450) · ddee21cb
  KrishnanPrash authored Jan 16, 2026
  
  ddee21cb
- fix: include missing reqs in benchmark (#5477) · abe9d127
  Yan Ru Pei authored Jan 16, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  abe9d127
- chore: make precentile plots in router benchmark (#5476) · d83ab662
  Yan Ru Pei authored Jan 16, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  d83ab662
- build: Install NVIDIA packages based on CUDA version (#5461) · 34c4882d
  Pavithra Vijayakrishnan authored Jan 15, 2026
```
Signed-off-by: pvijayakrish <pvijayakrish@nvidia.com>
Signed-off-by: Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>
```
  34c4882d
15 Jan, 2026 1 commit
- fix: [vLLM multimodel] launch image loading in parallel (#5444) · 0b7e1271
  GuanLuo authored Jan 15, 2026
```
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
```
  0b7e1271