Commits · 7b967c77efc0987aaab611e2edce24ff1daee6b5 · OpenDAS / dynamo

"examples/vscode:/vscode.git/clone" did not exist on "add1b9d3dec4a6d1b404f5793a210ff77482b7ae"

18 Nov, 2025 5 commits

fix: Mark enable_kv_events=True for user-specified vLLM KVEventsConfig in scripts (#4418) · 7b967c77
Karen Chung authored Nov 18, 2025
```
Signed-off-by: Karen Chung <karenc@nvidia.com>
```
7b967c77
fix: add kv events config in agg_router sglang example (#4391) · cf64ca7c
Vladislav Nosivskoy authored Nov 18, 2025
```
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
```
cf64ca7c
fix: Move trtllm multimodal worker to use ModelInput.Token (#4373) · c3984bc2
Indrajit Bhosale authored Nov 17, 2025
```
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
```
c3984bc2
fix: Fix port collision and pass prefill param in kvbm connector (#4411) · e3cee95f
Kris Hung authored Nov 17, 2025
```
Signed-off-by: krishung5 <krish@nvidia.com>
```
e3cee95f

docs: Clean up incomplete recipes and clarify Kubernetes-only focus (#4159) · 88dfd1b3

Ben Hamm authored Nov 17, 2025


Signed-off-by: Ben Hamm <ben.hamm@gmail.com>
Signed-off-by: Tanmay Verma <tanmay2592@gmail.com>
Signed-off-by: atchernych <atchernych@nvidia.com>
Co-authored-by: Biswa Panda <biswa.panda@gmail.com>
Co-authored-by: tanmayv25 <tanmay2592@gmail.com>
Co-authored-by: Tanmay Verma <tanmayv@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: atchernych <atchernych@nvidia.com>

88dfd1b3

17 Nov, 2025 3 commits
- fix: workaround vllm prometheus cleanup error on shutdown (#4323) · 6afb4d5b
  Keiven C authored Nov 17, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  6afb4d5b
- feat: Command line flag to set request plane mode: tcp, http or nats (#4365) · 886506c1
  Graham King authored Nov 17, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  886506c1
- fix: fix trtllm multinode DGD (#4389) · 9f3d1b90
  Julien Mancuso authored Nov 17, 2025
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  9f3d1b90
15 Nov, 2025 1 commit
- docs: Update vllm multimodal EPD doc (#4352) · 1e120ed0
  Kris Hung authored Nov 15, 2025
  
  1e120ed0
14 Nov, 2025 3 commits

fix: rm dynamoNamespace from GAIE example (#4313) · 84737baf

atchernych authored Nov 14, 2025


Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
Signed-off-by: atchernych <atchernych@nvidia.com>

84737baf

fix: misnamed tensorrtllm-runtime image and incorrect tag (#4289) · a4eb4e8a

Harrison Saturley-Hall authored Nov 14, 2025

Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Harrison Saturley-Hall <harrison.saturley.hall@gmail.com>
Co-authored-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>

a4eb4e8a

fix(vllm): port allocation bugs leading to zmq error (#4321) · ecf6d48c
Alec authored Nov 13, 2025
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
```
ecf6d48c

13 Nov, 2025 3 commits
- feat: Add vLLM multimodal audio support (#2760) · 0f5dd2b7
  Yuekai Zhang authored Nov 14, 2025
```
Signed-off-by: Yuekai Zhang <zhangyuekai@foxmail.com>
Signed-off-by: krishung5 <krish@nvidia.com>
Co-authored-by: Kris Hung <krish@nvidia.com>
```
  0f5dd2b7
- feat: transport agnostic request plane for dynamo - natless (#4246) · 06b0ebef
  Biswa Panda authored Nov 13, 2025
  
  06b0ebef
- chore: llama4 multimodal disagg support migration (#4213) · 4adab52d
  Ayush Agarwal authored Nov 13, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  4adab52d
12 Nov, 2025 2 commits
- feat: agg support + solidfy fp8 configs (#3886) · f8219b12
  ishandhanani authored Nov 12, 2025
  
  f8219b12
- feat: add --enable-otel flag to SGLang launch scripts (#4243) · 5fd96a23
  ishandhanani authored Nov 11, 2025
  
  5fd96a23
11 Nov, 2025 1 commit
- chore: Remove static mode (#4235) · e1af3af6
  Graham King authored Nov 11, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  e1af3af6
10 Nov, 2025 3 commits

refactor: consolidate Observability files (e.g. OTEL docker-compose, md files) (#4173) · afccc9d4

Keiven C authored Nov 10, 2025


Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>

afccc9d4

feat: remove PVC logic from profiler planner (#4210) · fa6a7f94

hhzhang16 authored Nov 10, 2025


Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: hongkuanz <hongkuanz@nvidia.com>

fa6a7f94

chore: mm epd disagg (#4151) · 06bc1580
Ayush Agarwal authored Nov 09, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
06bc1580

07 Nov, 2025 3 commits
- feat: deprecate DYN_SYSTEM_ENABLED in favor of DYN_SYSTEM_PORT (#4082) · 6bccf099
  Keiven C authored Nov 07, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  6bccf099
- refactor: align multimodal example port allocation with vLLM components (#4163) · 6f8fd865
  Neelay Shah authored Nov 07, 2025
```
Co-authored-by: Claude <noreply@anthropic.com>
```
  6f8fd865
- feat(keyvalue): Filesystem backed KeyValueStore (#4138) · 794c0a44
  Graham King authored Nov 07, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  794c0a44
06 Nov, 2025 2 commits
- refactor: remove port reservation system in favor of manual specification (#4142) · a629b86a
  Alec authored Nov 05, 2025
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
```
  a629b86a
- feat: Add base64 and HTTP image URL support to vLLM workers (#4114) · b73c571f
  KrishnanPrash authored Nov 05, 2025
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  b73c571f
05 Nov, 2025 2 commits
- chore: trtllm use unified frontend (#4097) · 9fa8125c
  Yan Ru Pei authored Nov 04, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  9fa8125c
- fix: update planner + docs now that profiling results are stored in /data (#4098) · 5528f3b4
  hhzhang16 authored Nov 04, 2025
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  5528f3b4
04 Nov, 2025 3 commits
- fix: add prefill metrics support for TensorRT-LLM disaggregated mode (#3983) · ba51c683
  Keiven C authored Nov 04, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  ba51c683
- fix: add prefill metrics support for SGLang disaggregated mode (#3992) · 49ecfe60
  Keiven C authored Nov 04, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  49ecfe60
- fix: update router standalone to use updated vLLM API (#4079) · 81b8af8d
  Sean SH Choi authored Nov 03, 2025
```
Signed-off-by: Sean Choi <sechoi@nvidia.com>
```
  81b8af8d
03 Nov, 2025 2 commits
- fix: vllm disagg launch script should not enable kv routing (#4063) · 2d7f5fc5
  Yan Ru Pei authored Nov 03, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  2d7f5fc5
- chore: disagg + router k8s recipe minor changes (#4050) · ba99d24a
  Yan Ru Pei authored Nov 03, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  ba99d24a
01 Nov, 2025 1 commit
- feat: restructure dsr1 recipes and add gb200 (#3891) · b73e6eb5
  Rohan Varma authored Oct 31, 2025
```
Signed-off-by: Rohan Varma <rohanv@nvidia.com>
```
  b73e6eb5
31 Oct, 2025 3 commits
- fix: use full path for recipes directory (#3989) · 17139df9
  Anant Sharma authored Oct 31, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  17139df9
- fix: move new files from components to examples backend (#4023) · e6809ff0
  Anant Sharma authored Oct 31, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  e6809ff0
- refactor: move backend deploy, launch and slurm files from components to examples (#3849) · 8bd37c96
  Anant Sharma authored Oct 31, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  8bd37c96
30 Oct, 2025 1 commit
- chore: support for agg llama4 mulimodal (#3984) · 22d910a5
  Ayush Agarwal authored Oct 30, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  22d910a5
29 Oct, 2025 1 commit
- feat: refactor vllm multimodal example (#3634) · 52090e2e
  Ayush Agarwal authored Oct 29, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  52090e2e
28 Oct, 2025 1 commit
- chore(runtime): Do not expose etcd lease ID (#3915) · c78b5901
  Graham King authored Oct 28, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  c78b5901