Commits · 359765d3546f774c9dc85cc0bbca6ca135337f78 · OpenDAS / dynamo · GitLab

14 Feb, 2026 3 commits
- feat: load-based scaling in SLA Planner (#6145) · 359765d3
  Hongkuan Zhou authored Feb 14, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  359765d3
- feat: mm aware routing for vllm (#6235) · 815b1291
  zhongdaor-nv authored Feb 13, 2026
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
Signed-off-by: zhongdaor-nv <zhongdaor@nvidia.com>
```
  815b1291
- feat: migrate GPU discovery from Dynamo Profiler to Dynamo Operator with... · d56439ec
  hhzhang16 authored Feb 13, 2026
```
feat: migrate GPU discovery from Dynamo Profiler to Dynamo Operator with automatic injection (#6224)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  d56439ec
13 Feb, 2026 12 commits
- feat: Enable ModelExpress P2P weight transfer in Dynamo vLLM worker (#6186) · 233a1e9a
  Hyunjae Woo authored Feb 13, 2026
```
Signed-off-by: Hyunjae Woo <hwoo@nvidia.com>
```
  233a1e9a
- Rename fetch_llm to fetch_model (#6268) · 5624d144
  Tzu-Ling Kan authored Feb 13, 2026
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  5624d144
- fix: consolidate dyn_discovery_backend and dyn_kv_store (#6167) · a289695c
  mohammedabdulwahhab authored Feb 13, 2026
```
Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
```
  a289695c
- fix: vLLM decode worker logging format bug causing CrashLoopBackOff (#6267) · 4e50a3f3
  Tushar Sharma authored Feb 13, 2026
```
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  4e50a3f3
- test: vllm conformance tests for the new frontend processing APIs (#6256) · 98df1a2c
  Graham King authored Feb 13, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  98df1a2c
- feat: add video generation support (T2V) (#5793) · 2be83be2
  ishandhanani authored Feb 13, 2026
  
  2be83be2
- chore: rename KvPushRouter to KvRouter in python + more bindings removal (#6238) · 14eceb43
  Yan Ru Pei authored Feb 12, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  14eceb43
- feat: Decomposed pipeline for EPP integration [DEP-730] (#5446) · 52271760
  atchernych authored Feb 12, 2026
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  52271760
- feat: add encode client and embedding cache to PD worker (#6029) · cb88fdc7
  Qi Wang authored Feb 12, 2026
  
  cb88fdc7
- fix(sglang): lazy-import prometheus_client to fix TokenizerMetricsCollector metrics (#6269) · d3fb7d57
  ishandhanani authored Feb 12, 2026
```
Signed-off-by: Ishan Dhanani <ishandhanani@gmail.com>
```
  d3fb7d57
- feat: router priority queue (#6010) · bc514fbe
  Yan Ru Pei authored Feb 12, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
```
  bc514fbe
- feat: Refactor frontend CLI configuration (#6201) · a82acfa0
  jh-nv authored Feb 12, 2026
  
  a82acfa0
12 Feb, 2026 8 commits
- chore: Remove dynamo-run and mistral-rs engine (#6203) · bbe82f18
  Graham King authored Feb 12, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  bbe82f18
- feat: Use SGLang MMEncoder for multimodal EPD encode worker (#6162) · 3967ec0f
  KrishnanPrash authored Feb 12, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  3967ec0f
- feat: support AIC DGD gen call (WILL BREAK DGDR) (#6216) · a04b5631
  Hongkuan Zhou authored Feb 12, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  a04b5631
- feat: Flash Indexer (#5785) · 937398cf
  Yan Ru Pei authored Feb 11, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Signed-off-by: jthomson04 <jothomson@nvidia.com>
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Signed-off-by: Janelle Cai <jcai18@mit.edu>
Co-authored-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: Janelle Cai <jcai18@mit.edu>
```
  937398cf
- feat: Migrate vllm configuration system (#6075) · de27efe6
  jh-nv authored Feb 12, 2026
  
  de27efe6
- feat: request migration for SGLang (#5659) · b94f9dcd
  jh-nv authored Feb 11, 2026
  
  b94f9dcd
- docs: migrate Fern docs from fern/ into docs/ (#6206) · 39d645e5
  Jonathan Tong authored Feb 11, 2026
```
Signed-off-by: Jont828 <jt572@cornell.edu>
```
  39d645e5
- feat(chrek): config refactor, /dev/shm support, and mount-policy rewrite (#5946) · d381e6ff
  Schwinn Saereesitthipitak authored Feb 11, 2026
  
  d381e6ff
11 Feb, 2026 6 commits
- fix: restrict Image.open() formats to prevent PSD parsing (workaround) (#6212) · b6824ae0
  dagil-nvidia authored Feb 11, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
```
  b6824ae0
- fix: Cleanup pytest markers, enable gpu_0 tests on trtllm arm, reduce log noise (#6124) · 4220771f
  Dmitry Tokarev authored Feb 11, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  4220771f
- fix: convert guided_decoding dict to GuidedDecodingParams in TRT-LLM handler (#6127) · 5602dd2f
  Yuewei Na authored Feb 11, 2026
```
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
```
  5602dd2f
- chore: Merge bindings client and client2 functions (#6158) · 73dc3be8
  Graham King authored Feb 11, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  73dc3be8
- feat: add Prometheus auto and custom label injection for engine metrics (#5989) · e18840ce
  Keiven C authored Feb 10, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  e18840ce
- feat: add embedding transfer sender and receiver (#6098) · 67d00b24
  GuanLuo authored Feb 10, 2026
```
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
```
  67d00b24
10 Feb, 2026 9 commits
- refactor: move worker init logic from main.py to workers/ module (#6063) · be9adb34
  Yuewei Na authored Feb 10, 2026
```
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
```
  be9adb34
- feat(frontend): Use vllm for pre and post processing (#5544) · 4f99451b
  Graham King authored Feb 10, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  4f99451b
- feat: add video diffusion support to TRTLLM backend (wan_t2v only) (#5926) · df2daadd
  Yuewei Na authored Feb 10, 2026
```
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Signed-off-by: Yuewei Na <248773860+nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Tanmay Verma <tanmayv@nvidia.com>
```
  df2daadd
- ci: apply static type check to vllm multimodal handlers (#6027) · ae09b929
  Qi Wang authored Feb 10, 2026
  
  ae09b929
- refactor: add prefill_worker_utils in vLLM (#6017) · 20ccc9b2
  Qi Wang authored Feb 10, 2026
  
  20ccc9b2
- chore: consistent name -- MultimodalEmbeddingCache (#5962) · df8fd92b
  Qi Wang authored Feb 10, 2026
  
  df8fd92b
- feat: base classes for the configuration system (#5975) · bf6840e6
  jh-nv authored Feb 10, 2026
  
  bf6840e6
- feat: expose Python Prometheus metric via DynamoComponentMetrics (#5817) · 027d2653
  Keiven C authored Feb 09, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  027d2653
- feat: Add SGLang /engine weight update endpoints (#6094) · 56a1b6e3
  William Arnold authored Feb 09, 2026
  
  56a1b6e3
09 Feb, 2026 2 commits
- feat: text to image vLLM Omni (#5912) · 9f76d060
  Ayush Agarwal authored Feb 09, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  9f76d060
- refactor: use tempfile module instead of hardcoded /tmp paths (#5789) · 0ef41ffe
  dagil-nvidia authored Feb 09, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
```
  0ef41ffe