Commits · a5049f0fc63e7ae552b0b9690c9408b01d0612ce · OpenDAS / dynamo

26 Nov, 2025 1 commit
- fix: inject TRTLLM_USE_UCX_KVCACHE env var in mpirun (#4609) · a5049f0f
  Rohan Varma authored Nov 25, 2025
  
  a5049f0f
25 Nov, 2025 21 commits
- refactor(storage): Remove the stuttering from key_value_store. (#4604) · fcb91e4b
  Graham King authored Nov 25, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  fcb91e4b
- chore: make loading planner profile data one-stage for mockers (#4590) · 7a384793
  Yan Ru Pei authored Nov 25, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  7a384793
- chore: make router use the discovery pattern instead of manual kv watch (#4597) · 9c5018e5
  Yan Ru Pei authored Nov 25, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  9c5018e5
- docs: remove frontend image from support matrix (#4589) · 445b4bd9
  dagil-nvidia authored Nov 25, 2025
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  445b4bd9
- fix: update ai-dynamo[vllm] version and pin transformers (#4592) · ef0a4721
  dagil-nvidia authored Nov 25, 2025
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  ef0a4721
- chore: update pvc name for trtllm dsr1 recipe (#4595) · 6e9782ba
  Hongkuan Zhou authored Nov 25, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  6e9782ba
- feat: Enable intel gaudi on dynamo (#4209) · d0e3b7b7
  Sihan Chen authored Nov 26, 2025
```
Signed-off-by: Spycsh <sihan.chen@intel.com>
```
  d0e3b7b7
- chore(runtime): Make nats_client private, refactor NATS stats scraping (#4591) · 17dcffe8
  Graham King authored Nov 25, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  17dcffe8
- fix: Fix vllm MM aggregated mode Corner Case (#4583) · c90e3dff
  Indrajit Bhosale authored Nov 25, 2025
  
  c90e3dff
- feat: decoded media via NIXL (#3988) · 0a065918
  milesial authored Nov 25, 2025
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
Signed-off-by: Ayush Agarwal <ayushag@nvidia.com>
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
Co-authored-by: Ayush Agarwal <ayushag@nvidia.com>
Co-authored-by: Krishnan Prashanth <kprashanth@nvidia.com>
Co-authored-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com>
```
  0a065918
- fix: dsr1 recipe download pvc name (#4566) · b5db4e75
  Hongkuan Zhou authored Nov 25, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  b5db4e75
- refactor(llm): Rename EngineConfig::Static to InProcess (#4585) · 0fc5273c
  Graham King authored Nov 25, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  0fc5273c
- feat: allow dynamic port in scripts in preparation for parallel testing (part 1) (#4546) · a77558d4
  Keiven C authored Nov 25, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  a77558d4
- fix: prevent cluster-wide operator from reconciling DGDR/DynamoModel in... · 0a8b917e
  Julien Mancuso authored Nov 25, 2025
```
fix: prevent cluster-wide operator from reconciling DGDR/DynamoModel in namespaces with namespace-restricted operator (#4574)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  0a8b917e
- docs: update TensorRT-LLM commit for NIXL to v1.2.0rc2 (#4582) · 93c81420
  dagil-nvidia authored Nov 25, 2025
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  93c81420
- chore(runtime): Tidy up component paths (#4560) · 51c1b9f1
  Graham King authored Nov 25, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  51c1b9f1
- fix: Dockerfile.trtllm - install triton when building from source on arm (#4579) · 4babb33c
  Dmitry Tokarev authored Nov 25, 2025
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  4babb33c
- fix: expose prefill worker id in disagg (#4563) · 57c701fb
  Yan Ru Pei authored Nov 24, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  57c701fb
- feat: Add security flag to MM flow in vllm (#4556) · 550bf98c
  Indrajit Bhosale authored Nov 24, 2025
```
Co-authored-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com>
```
  550bf98c
- ci: Pin transformers version to 4.57.1 (#4561) · ef8cf365
  KrishnanPrash authored Nov 24, 2025
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
Co-authored-by: Tushar Sharma <tusharma@nvidia.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  ef8cf365
- fix: Increase the failure threshold for k8s dsr1 trtllm wideep deploy.yaml (#4557) · d6aa4a0b
  Tanmay Verma authored Nov 24, 2025
  
  d6aa4a0b
24 Nov, 2025 2 commits
- docs: update support matrix for Dynamo 0.7.0 (#4550) · 25fd32ab
  dagil-nvidia authored Nov 24, 2025
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  25fd32ab
- fix(dynamo-run): Run without etcd/nats, HTTP port to 8000 (#4555) · e75bcf67
  Graham King authored Nov 24, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  e75bcf67
23 Nov, 2025 1 commit
- feat: Better cublas support in vLLM container. (#4514) · f0ca16f0
  jthomson04 authored Nov 23, 2025
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
```
  f0ca16f0
22 Nov, 2025 4 commits

feat: Add k8s Fault Tolerance Validations infra (#4067) · c0e394d5

Indrajit Bhosale authored Nov 21, 2025


Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: Claude <noreply@anthropic.com>

c0e394d5

chore: upgrade trtllm 1.2.0rc2 (#4405) · 9b8b9988

Dmitry Tokarev authored Nov 21, 2025


Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Co-authored-by: tanmayv25 <tanmay2592@gmail.com>
Co-authored-by: Kyle McGill <kmcgill@nvidia.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
Co-authored-by: Tanmay Verma <tanmayv@nvidia.com>

9b8b9988

chore: unify LMCache UX w/ and w/o Dynamo (#4509) · 6d69e8c7
Ziqi Fan authored Nov 21, 2025
```
Signed-off-by: Ziqi Fan <ziqif@nvidia.com>
```
6d69e8c7
fix: health check endpoint (#4522) · b1286e7f
Biswa Panda authored Nov 21, 2025

b1286e7f

21 Nov, 2025 11 commits
- chore: Make nats_client private at crate level, various tidy up (#4513) · f05f7629
  Graham King authored Nov 21, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  f05f7629
- fix(storage): Correctly encoding FileStore keys (#4539) · 27904535
  Graham King authored Nov 21, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  27904535
- chore: split frontend + runtime launch message to accurately represent container purpose (#4537) · f2769d88
  Tushar Sharma authored Nov 21, 2025
```
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
Co-authored-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
```
  f2769d88
- fix: fix PVC in shared frontend example (#4517) · b7667c48
  Julien Mancuso authored Nov 21, 2025
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  b7667c48
- fix: better instructions for GAIE recipe (#4525) · b6f31b41
  atchernych authored Nov 21, 2025
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  b6f31b41
- docs: Add Recipes to ToC and bump FW Support Matrix further up (#4536) · cb2ea1be
  Harry Kim authored Nov 21, 2025
```
Signed-off-by: Harry Kim <harry_kim@live.com>
```
  cb2ea1be
- chore: merge KvIndexer and ApproxKvIndexer (#4500) · c61e0dd3
  Yan Ru Pei authored Nov 21, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  c61e0dd3
- fix: worker_id updates not applied (#4518) · 989e246e
  Zhongxuan (Daniel) Wang authored Nov 21, 2025
```
Signed-off-by: Zhongxuan (Daniel) Wang <daniewang@nvidia.com>
```
  989e246e
- chore: parallelize planner profile tests + bindings test cleanup (#4532) · d821a8b9
  Yan Ru Pei authored Nov 21, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  d821a8b9
- feat: Xml coder tool parser (#4415) · 65f18884
  William Zhang authored Nov 21, 2025
```
This commit adds a parser implementation for Xml style
tool calls, based currently on Qwen3 coder.

Followup work needs to be done to make it more generic
and parameterizable.
```
  65f18884
- fix: set `SGLANG_BLOCK_NONZERO_RANK_CHILDREN` to be no-op (#4527) · 6b432625
  ishandhanani authored Nov 20, 2025
  
  6b432625