Commits · ba2d9684bfb7132c3608ea77736d99a8d44b1acd · OpenDAS / dynamo

18 Mar, 2026 3 commits
- docs: add mocker under testing (#7488) · 3357c53f
  Yan Ru Pei authored Mar 18, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  3357c53f
- chore: add vllm omni e2e tests (#7454) · f890199f
  Ayush Agarwal authored Mar 18, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  f890199f
- refactor: clean up checkpoint orchestration (#7309) · 38bb9d37
  Schwinn Saereesitthipitak authored Mar 18, 2026
```
Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
```
  38bb9d37
17 Mar, 2026 1 commit

feat(mocker): add SGLang engine simulation (#6977) · 930721c8

Yongming Ding authored Mar 17, 2026


Signed-off-by: Yongming Ding <yongmingd@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

930721c8

16 Mar, 2026 2 commits
- feat: vllm omni cli (#6788) · f81f5277
  Ayush Agarwal authored Mar 16, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  f81f5277
- feat: dynamic CLI flags for trtllm (#7335) · 3882cba4
  jh-nv authored Mar 16, 2026
  
  3882cba4
15 Mar, 2026 1 commit
- feat: integrate fastokens BPE tokenizer backend (#7387) · da810a26
  Biswa Panda authored Mar 15, 2026
  
  da810a26
14 Mar, 2026 2 commits
- feat: standalone KV indexer runtime integration (#7295) · bba70a41
  Thomas Montfort authored Mar 14, 2026
  
  bba70a41
- feat: propagate OTEL trace context across E/P/D multimodal workers (#7239) · c263a99e
  jh-nv authored Mar 13, 2026
  
  c263a99e
13 Mar, 2026 7 commits
- fix: populate logprobs bytes and token fields in OpenAI-compatible responses (#6953) · 947939c7
  Biswa Panda authored Mar 13, 2026
  
  947939c7
- fix: reject multimodal requests when worker lacks --modality multimodal (#7065) · 4105de62
  KrishnanPrash authored Mar 13, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  4105de62
- feat(mocker): add --decode-speedup-ratio for speculative decoding simulation (#7349) · 7e07495f
  Yan Ru Pei authored Mar 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  7e07495f
- fix: inject tolerations for interpolation (profiling) (#7344) · 20f1c5a3
  hhzhang16 authored Mar 13, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  20f1c5a3
- feat: Add NVTX markers for sglang EPD (#7079) · f29753dc
  Wang, Yi authored Mar 14, 2026
```
Signed-off-by: Wang, Yi <yi.a.wang@intel.com>
```
  f29753dc
- feat(kv-router): pluggable scheduling policy for router queue [DYN-2454] (#7260) · bddaaa26
  Yan Ru Pei authored Mar 12, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  bddaaa26
- chore(deps): bump vLLM 0.16.0 → 0.17.1 (#7170) · dba69e0f
  Tzu-Ling Kan authored Mar 12, 2026
```
Signed-off-by: Tzu-Ling <tzulingk@nvidia.com>
```
  dba69e0f
12 Mar, 2026 8 commits
- feat: ForwardPassMetrics dynamo event plane integration (#7250) · cd4773fb
  Hongkuan Zhou authored Mar 12, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  cd4773fb
- feat(kv-router): ZMQ gap detection + replay for standalone indexer [LLM-126] (#7209) · bb07b2f4
  Yan Ru Pei authored Mar 12, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  bb07b2f4
- feat: vllm omni image to video support (#6530) · 1182e207
  Ayush Agarwal authored Mar 12, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  1182e207
- docs: add docs for DGDR usage -- golden path (#6946) · 5c7e66ec
  hhzhang16 authored Mar 12, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  5c7e66ec
- feat: replaces PersistentConnector monkey-patch with proper nixl_conn… (#6913) · 387100c8
  Daniel Socek authored Mar 11, 2026
```
Signed-off-by: Daniel Socek <daniel.socek@intel.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  387100c8
- fix: address sglang failures on pre-merge/post-merge workflows (#7255) · cdb7218a
  Tushar Sharma authored Mar 11, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  cdb7218a
- chore(vllm): expand qwen3 vl multimodal support list (#6163) · 6a46e3a0
  Daniel Socek authored Mar 11, 2026
```
Signed-off-by: Daniel Socek <daniel.socek@intel.com>
```
  6a46e3a0
- fix: vision model loader fixes (#6952) · f01a5c71
  Daniel Socek authored Mar 11, 2026
```
Signed-off-by: Daniel Socek <daniel.socek@intel.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  f01a5c71
11 Mar, 2026 10 commits
- feat: streaming tool call and reasoning dispatch SSE events (#7114) · 5178a4a4
  MatejKosec authored Mar 11, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  5178a4a4
- chore: add context manager based timer (#7007) · d16862ad
  GuanLuo authored Mar 11, 2026
```
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
```
  d16862ad
- feat: GlobalPlanner --max-total-gpus for cluster-wide GPU budget (#7103) · 5d5fd243
  daiyaanarfeen authored Mar 11, 2026
```
Signed-off-by: Daiyaan <darfeen@nvidia.com>
Signed-off-by: athreesh <anish.maddipoti@utexas.edu>
Signed-off-by: Anish <80174047+athreesh@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: athreesh <anish.maddipoti@utexas.edu>
Co-authored-by: Anish <80174047+athreesh@users.noreply.github.com>
```
  5d5fd243
- feat: add generate health check support for PD SGLang (#6004) · cf5f65f7
  Vladislav Nosivskoy authored Mar 12, 2026
```
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
```
  cf5f65f7
- feat: apply DGD overrides before running interpolation (#7226) · 5fd39ade
  hhzhang16 authored Mar 11, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  5fd39ade
- test(frontend): Minimal integration test for vllm processor (#7173) · fda022b1
  Graham King authored Mar 11, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  fda022b1
- feat: forward pass metric via ZMQ in vllm (#7200) · af30b779
  Hongkuan Zhou authored Mar 11, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  af30b779
- fix: serialize disagg first_gen_log_probs int keys for Rust transport (#7145) · e930526b
  Yuewei Na authored Mar 10, 2026
```
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
```
  e930526b
- feat: hide optimizationType (#7160) · 611e856d
  hhzhang16 authored Mar 10, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  611e856d
- feat(anthropic): add thinking block support and preamble stripping to /v1/messages (#7137) · 012236ee
  MatejKosec authored Mar 10, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  012236ee
10 Mar, 2026 6 commits
- fix: set correct component type in agg planner (#7176) · f435da14
  Hongkuan Zhou authored Mar 10, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  f435da14
- fix: resolve 'auto' backend to concrete value in every situation (#7158) · 0c6a8024
  hhzhang16 authored Mar 10, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  0c6a8024
- fix: only add profiling data to mocker workers (#7164) · 14d928cb
  Hongkuan Zhou authored Mar 10, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  14d928cb
- fix(perf): Skip duplicate image downloads and unnecessary image processing in... · 6634f33f
  zhongdaor-nv authored Mar 10, 2026
```
fix(perf): Skip duplicate image downloads and unnecessary image processing in MM Router (vLLM) (#7080)
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
Signed-off-by: zhongdaor-nv <zhongdaor@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  6634f33f
- fix(mocker): align vLLM scheduler with v1 — drop watermark, LIFO preemption, retry loop (#7020) · 236cb17d
  Yan Ru Pei authored Mar 10, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  236cb17d
- fix: propagate resolved backend and skip interpolation for aggregated configs (#7106) · 50818575
  hhzhang16 authored Mar 09, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  50818575