Commits · 8c8680b179c1e7fc13fb8c79100386561dc5dd99 · OpenDAS / dynamo · GitLab

05 Feb, 2026 10 commits
- feat: Make grpc startup dynamic for high ISL/OSL in GRPC frontend (#5536) · 8c8680b1
  Indrajit Bhosale authored Feb 05, 2026
```
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
```
  8c8680b1
- ci: xfail failing chunked_prefill_offload test and fix ucx tag (#6006) · 20847a6e
  Anant Sharma authored Feb 05, 2026
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  20847a6e
- ci: deploy tests fix (#5996) · 458b2066
  Ran Rubin authored Feb 05, 2026
  
  458b2066
- docs: add documentation templates for streamlined docs structure (#5834) · 3a9bfc48
  dagil-nvidia authored Feb 05, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
```
  3a9bfc48
- ci: Using Dynamo Builder (#5914) · 6ac17b99
  Ran Rubin authored Feb 05, 2026
  
  6ac17b99
- fix: ignore benchmarks pytest for now (#5983) · 50e17783
  Yan Ru Pei authored Feb 05, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  50e17783
- fix: e2e aiperf profiling on NAT dataset (#5990) · 88efa735
  Yan Ru Pei authored Feb 04, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  88efa735
- fix: Add mpi arg to all srun commands (#5948) · 910d74f5
  Ryan McCormick authored Feb 05, 2026
  
  910d74f5
- fix: update aiperf version (#5982) · 16956ac6
  Yan Ru Pei authored Feb 04, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  16956ac6
- feat: remove default model name in Profiler; validate for one of served model... · 7e4bc716
  hhzhang16 authored Feb 04, 2026
```
feat: remove default model name in Profiler; validate for one of served model name and model path in Profiler (#5950)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  7e4bc716
04 Feb, 2026 30 commits
- fix: fix for how vllm disseminates cached requests to kvbm (#5851) · 3a2885c8
  Kyle McGill authored Feb 04, 2026
```
Signed-off-by: Kyle McGill <kmcgill@nvidia.com>
```
  3a2885c8
- feat: use encoder cache in TRT-LLM EPD workflow (#5780) · a78a4260
  Qi Wang authored Feb 04, 2026
  
  a78a4260
- feat: read prefill/decode worker counts from DGD status (#5934) · b12e6710
  Thomas Montfort authored Feb 04, 2026
  
  b12e6710
- docs: fix markdown formatting in Distributed_Inference README (#5947) · ef292944
  dagil-nvidia authored Feb 04, 2026
  
  ef292944
- fix: treat `--tool-call-parser` and `--dyn-tool-call-parser` independently for SGLang (#5849) · cd3f9bbd
  KrishnanPrash authored Feb 04, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  cd3f9bbd
- chore: use aiperf utils in prefix synthesizer (#5906) · 4fcee92f
  Yan Ru Pei authored Feb 04, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  4fcee92f
- feat: introduce cuda_ipc for TRT-LLM PrefillHandler (#5773) · 6cb76b96
  Qi Wang authored Feb 04, 2026
  
  6cb76b96
- test: indexer and full router benchmarks (#5784) · 039d35ff
  Janelle Cai authored Feb 04, 2026
  
  039d35ff
- chore: Increase E2E 1-GPU Test Timeout (#5888) · 051f18a4
  Jacky authored Feb 04, 2026
```
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
```
  051f18a4
- fix: correct restart state for parallel restarts (#5949) · 94d82a48
  Julien Mancuso authored Feb 04, 2026
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
Co-authored-by: tmontfort <tmontfort@nvidia.com>
```
  94d82a48
- feat: Add per-worker Prometheus metrics for router load monitoring (#5842) · 0c0336e6
  Hongkuan Zhou authored Feb 04, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  0c0336e6
- fix: Wrap default_multimodal_input_loader in asyncio.to_thread (#5945) · eff08aed
  Indrajit Bhosale authored Feb 04, 2026
  
  eff08aed
- fix: update disagg tracing screenshot and description (#5956) · f3bea5d5
  jh-nv authored Feb 04, 2026
  
  f3bea5d5
- chore: linux gate lib/memory (#5942) · 67df0065
  Yan Ru Pei authored Feb 04, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  67df0065
- feat: basic vllm omni pipeline support (#5608) · 76e0e207
  Ayush Agarwal authored Feb 04, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  76e0e207
- feat: Various Mocker Perf improvements + fixes (#5808) · d22ca523
  jthomson04 authored Feb 04, 2026
```
Signed-off-by: jthomson04 <jothomson@nvidia.com>
```
  d22ca523
- chore: rename terminate_existing to terminate_all_matching_processes (#5923) · e55ebec5
  Keiven C authored Feb 04, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  e55ebec5
- docs: update support matrix with backend dependencies for Dynamo 0.9.0 + 1.0.0 (#5932) · 4d9e64a2
  dagil-nvidia authored Feb 04, 2026
  
  4d9e64a2
- feat: sccache metrics (#5177) · 04ec58c7
  Nate Mailhot authored Feb 04, 2026
```
Signed-off-by: Nate Mailhot <nmailhot@nvidia.com>
```
  04ec58c7
- fix: fuse unfold streams to prevent panics from poll after termination (#5872) · 7beb5f1a
  Janelle Cai authored Feb 04, 2026
  
  7beb5f1a
- fix: Multimodal disaggregation improvements (#5895) · 763264ff
  Daniel Socek authored Feb 04, 2026
```
Signed-off-by: Daniel Socek <daniel.socek@intel.com>
```
  763264ff
- fix: race between worker discovery and runtimeconfig discovery in KV router (#5924) · c7f6f6d9
  Janelle Cai authored Feb 03, 2026
```
Signed-off-by: Janelle Cai <jcai18@mit.edu>
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Yan Ru Pei <yanrpei@gmail.com>
```
  c7f6f6d9
- feat(lora): add lora load estimator (#5880) · 72a12869
  Biswa Panda authored Feb 03, 2026
  
  72a12869
- feat: add EncoderCacheManager to TRT-LLM PrefillHandler (#5714) · b82b45a1
  Qi Wang authored Feb 03, 2026
  
  b82b45a1
- fix: Add status file to prevent output-copier hang on failures (#5898) · 0268aea4
  hhzhang16 authored Feb 03, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  0268aea4
- docs: add overview doc for GPU Memory Service (GMS) (#5920) · 4f9a190c
  Biswa Panda authored Feb 03, 2026
```
Co-authored-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
```
  4f9a190c
- feat(planner): Derive prefill/decode GPU counts from DGD (#5919) · 2176c431
  Thomas Montfort authored Feb 03, 2026
  
  2176c431
- feat: default with lib/memory, media-nixl and kvbm (#5602) · 8daacbd7
  milesial authored Feb 03, 2026
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  8daacbd7
- docs: update (#5915) · 0862f87b
  Ran Rubin authored Feb 04, 2026
  
  0862f87b
- fix(runtime): return 500 on LoRA load/unload errors (#5626) · da0cbf68
  Ameen Patel authored Feb 03, 2026
```
Signed-off-by: AmeenP <ameenp360@gmail.com>
Co-authored-by: Biswa Panda <biswa.panda@gmail.com>
```
  da0cbf68