Commits · 6716de5513c8c2e07af0352c56ed7741768c6811 · OpenDAS / dynamo · GitLab

14 Jan, 2026 13 commits
- feat: frontend container attributions from EPP (#5435) · 6716de55
  Harrison Saturley-Hall authored Jan 14, 2026
```
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
```
  6716de55
- feat: SLA Planner configuration support for DEP and TEP VLLM (#4783) · 7cfd966e
  MatejKosec authored Jan 14, 2026
```
Extends the MOE planner profiler to support  TEP (tensor expert parallel) and DEP (data expert parallel) configs with the vllm backend
```
  7cfd966e
- fix: fix worker's push_handler non-blocking error upon stop word (#5157) · 31189eea
  Qi Wang authored Jan 14, 2026
  
  31189eea
- fix: update hello_world example to remove etcd (#5422) · 332da400
  Neal Vaidya authored Jan 14, 2026
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
```
  332da400
- fix: build.sh to use release branch for version detection (#5425) · 90ed9ab0
  Keiven C authored Jan 14, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  90ed9ab0
- fix: Clean up Velonix PR workflows (#5405) · 202dfc36
  Dillon Cullinan authored Jan 14, 2026
```
Signed-off-by: Dillon Cullinan <dcullinan@nvidia.com>
```
  202dfc36
- chore(router): Remove deprecated best_worker_id and metrics_labels (#5412) · c5458b99
  Graham King authored Jan 14, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  c5458b99
- fix: Properly handle multiple text components from request (#5196) · e22bb037
  jh-nv authored Jan 14, 2026
  
  e22bb037
- fix: ignore torchao SyntaxWarning in pytest filterwarnings (#5429) · 6fe88553
  dagil-nvidia authored Jan 14, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  6fe88553
- refactor: vllm EPD refactor (#4994) · 334cbd9b
  GuanLuo authored Jan 14, 2026
```
Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
```
  334cbd9b
- fix: mypy error (#5426) · 6f68be40
  Tzu-Ling Kan authored Jan 14, 2026
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  6f68be40
- refactor: remove "dev" stage from Dockerfile.* and centralize them into Dockerfile.dev (#5050) · 4816d639
  Keiven C authored Jan 13, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  4816d639
- fix: read store_kv arg from env when using decorator (#5421) · a936ba5a
  Neal Vaidya authored Jan 13, 2026
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
```
  a936ba5a
13 Jan, 2026 22 commits
- fix: Install numactl in TRTLLM container (#5367) · 2430fcac
  jthomson04 authored Jan 13, 2026
```
Signed-off-by: jthomson04 <jothomson@nvidia.com>
```
  2430fcac
- chore: Bump CUDA to 12.9.1 for vllm container (#5397) · 58a061f4
  Dmitry Tokarev authored Jan 13, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  58a061f4
- chore: use python apt for frontend container instead of uv (#5403) · af6eea0a
  Tushar Sharma authored Jan 13, 2026
```
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
```
  af6eea0a
- fix: Update TRT-LLM Wide-EP Disagg GB200 Recipe to be compatible with TRT-LLM Version (#5383) · a98406d4
  Rohan Varma authored Jan 13, 2026
  
  a98406d4
- chore: Revert KVBM v2 transfer integration (#5406) · 9ca2923d
  jthomson04 authored Jan 13, 2026
  
  9ca2923d
- docs: README updates for 0.8.0 (#5395) · 91a8d07f
  dagil-nvidia authored Jan 13, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
Signed-off-by: dagil-nvidia <dagil@nvidia.com>
```
  91a8d07f
- fix: use zero copy decoder for handling high concurrency / request bursts for tcp ingress (#5376) · bbb79afb
  Biswa Panda authored Jan 13, 2026
  
  bbb79afb
- fix: Bug 5792966 [DYN -1729] (#5385) · 1da603a4
  atchernych authored Jan 13, 2026
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  1da603a4
- fix: test_consolidator_router_e2e trtllm import failure (#5404) · 4be72b6f
  Qi Wang authored Jan 13, 2026
  
  4be72b6f
- build: disable cache export for frontend build in ci (#5365) · dfc0377a
  Tushar Sharma authored Jan 13, 2026
```
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
Signed-off-by: Dillon Cullinan <dcullinan92@gmail.com>
Co-authored-by: Dillon Cullinan <dcullinan92@gmail.com>
```
  dfc0377a
- fix: Move NATS max_payload from invalid CLI flag to config file (#5384) · a713270c
  Keiven C authored Jan 13, 2026
```
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  a713270c
- docs: add feature compatibility matrix and update support matrix for v0.8.0 (#5349) · 4ed8584a
  dagil-nvidia authored Jan 13, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
Signed-off-by: dagil-nvidia <dagil@nvidia.com>
```
  4ed8584a
- feat(model_card): Make bos_token_id optional (#5394) · dad42f42
  Graham King authored Jan 13, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  dad42f42
- feat: Propagate OTEL tracing context for trtllm (#5377) · 8c129ed4
  jh-nv authored Jan 13, 2026
  
  8c129ed4
- feat: add examples for kv state approximation based routing (#5320) · 869562da
  Biswa Panda authored Jan 13, 2026
  
  869562da
- chore: configure nemotron nano parsers (#5396) · 648e1cd2
  Ayush Agarwal authored Jan 13, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  648e1cd2
- chore: Update aiperf pinned version (#5331) · c3dc3de4
  Elias Bermudez authored Jan 13, 2026
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>
```
  c3dc3de4
- test: unit test tcp/client.rs handle_writer [1/n] (#5055) · e47457e4
  Qi Wang authored Jan 13, 2026
  
  e47457e4
- ci: remove deprecated parameters (#5390) · a170b31f
  Ran Rubin authored Jan 13, 2026
  
  a170b31f
- chore: Clean up vLLM DSR1 wideEP recipe (#5389) · 0bfe9822
  ptarasiewiczNV authored Jan 13, 2026
```
Signed-off-by: Piotr Tarasiewicz <ptarasiewicz@nvidia.com>
```
  0bfe9822
- docs: kv events (#5386) · 69e44e98
  Yan Ru Pei authored Jan 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  69e44e98
- fix: Replace NixlAgentMetadata with NixlHandshakePayload for vllm 0.13.0 (#5351) · 8a6efec6
  Kris Hung authored Jan 12, 2026
  
  8a6efec6
12 Jan, 2026 5 commits
- chore: explicitly install GPG package in containers (#5374) · 16451f48
  Tushar Sharma authored Jan 12, 2026
```
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
```
  16451f48
- feat: allow router not assuming decode kv reuse (#5350) · 7fdc742e
  Yan Ru Pei authored Jan 12, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  7fdc742e
- fix: Synchronizing on new thread to avoid delaing TRTLLM (#5333) · 329752d9
  Kyle McGill authored Jan 12, 2026
  
  329752d9
- fix: tag err (#5236) · 7952ea88
  ls-2018 authored Jan 13, 2026
```
Signed-off-by: acejilam <acejilam@gmail.com>
Co-authored-by: Graham King <grahamk@nvidia.com>
```
  7952ea88
- fix: GB200 mem allocation failure (#5328) · e3c3a6b9
  Qi Wang authored Jan 12, 2026
  
  e3c3a6b9