Commits · 1c77531a501dee670d4b1d71e198b857f451ca55 · OpenDAS / dynamo

15 Apr, 2025 3 commits
- docs: move deploy docs to docs/guides (#674) · 1c77531a
  hhzhang16 authored Apr 14, 2025
```
Signed-off-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>
Co-authored-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
```
  1c77531a
- docs: Use the same term for dynamo base image across code snippets and text (#670) · efb3e7d4
  Maksim Khadkevich authored Apr 14, 2025
```
Signed-off-by: Maksim Khadkevich <mkhadkevich@nvidia.com>
```
  efb3e7d4
- fix: set correct parent_hash for each kv block when publish kv events (#671) · 15455dff
  Ziqi Fan authored Apr 14, 2025
  
  15455dff
14 Apr, 2025 6 commits
- feat: add dynamoDeployment CR finalizer (#623) · 02a33f15
  julienmancuso authored Apr 14, 2025
  
  02a33f15
- feat(dynamo-run): improve available engines list in --help (#664) · cb0ceb81
  Xiaochuan Ye authored Apr 15, 2025
```
Signed-off-by: yexiaochuan <tap91624@gmail.com>
```
  cb0ceb81
- fix: deploy command should support passing config (#626) · 5b4e5496
  mohammedabdulwahhab authored Apr 14, 2025
```
Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
Co-authored-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>
Co-authored-by: Julien Mancuso <jmancuso@nvidia.com>
```
  5b4e5496
- fix: devcontainer mounts and vllm c api (#663) · 2d746153
  Alec authored Apr 14, 2025
  
  2d746153
- feat: add .devcontainer based off images in container/ (#497) · 0a86edc4
  Alec authored Apr 14, 2025
```
Co-authored-by: Ubuntu <ubuntu@crusoe-prod--inst-2secxwyxeao1mi2dsqk2pl9oaz7.eu-iceland1-a.comp>
Co-authored-by: Hannah Zhang <hannahz@nvidia.com>
Co-authored-by: hongkuanz <hongkuanz@nvidia.com>
```
  0a86edc4
- fix: signal handlers to clean up zombie vllm processes (#545) · 777e602b
  ishandhanani authored Apr 13, 2025
  
  777e602b
12 Apr, 2025 4 commits
- fix: change trtllm kv_router default block_size to 32 (#642) · 8edd23dc
  Ziqi Fan authored Apr 12, 2025
  
  8edd23dc
- fix: dynamo build should work with link syntax (#646) · 988e8826
  mohammedabdulwahhab authored Apr 12, 2025
  
  988e8826
- feat: ETCD prefix watcher + python binding + runtime reconfiguration for... · 08fd2897
  Hongkuan Zhou authored Apr 11, 2025
```
feat: ETCD prefix watcher + python binding + runtime reconfiguration for router and disagg router  (#581)
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
```
  08fd2897
- build: Define UCX env var to use NVLink when available (#631) · 1c67be28
  Tanmay Verma authored Apr 11, 2025
  
  1c67be28
11 Apr, 2025 13 commits

docs: Add documentation for UCX KV cache transfer in TRTLLM (#639) · 8d35dc43
Tanmay Verma authored Apr 11, 2025

8d35dc43
fix: adding conversion to string for notif id comparison (#638) · 3fa35f9e
Neelay Shah authored Apr 11, 2025

3fa35f9e
fix: serviceArgs in config was not getting set for workers (#640) · e3857ba0
mohammedabdulwahhab authored Apr 11, 2025

e3857ba0
fix: Update test_report (#641) · 5394421a
Pavithra Vijayakrishnan authored Apr 11, 2025
```
Signed-off-by: Pavithra Vijayakrishnan
```
5394421a

fix: Account for Metrics.decode() changes (#619) · c36794d9

Ryan McCormick authored Apr 11, 2025

- Replace custom StatsWithData object with library-defined Metrics object
- Update parsing logic to account for change to Metrics.decode()

c36794d9

fix: add DYNAMO_HOME env var to vLLM docker image (#629) · 6edf46c4
Anant Sharma authored Apr 11, 2025

6edf46c4
docs: Add instructions to install git lfs (#627) · ee986548
Tanmay Verma authored Apr 11, 2025

ee986548
fix: fix max_local_prefill_length not being printed out in disagg router log (#628) · 88e3779e
Hongkuan Zhou authored Apr 11, 2025

88e3779e
fix: Edit typos in dynamo deploy diagram (#615) · e7a49b03
mohammedabdulwahhab authored Apr 10, 2025

e7a49b03
docs: add docstring for llm.rs (#267) · 447840c2
Cole authored Apr 10, 2025

447840c2

feat: TRT-LLM disaggregated serving using UCX (#562) · da38e96a

Tanmay Verma authored Apr 10, 2025


Signed-off-by: Tanmay Verma <tanmay2592@gmail.com>
Signed-off-by: Tanmay Verma <tanmayv@nvidia.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>

da38e96a

docs: Guide for multi-node benchmarking (#561) · 538b4630

Jacky authored Apr 10, 2025

Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: Meenakshi Sharma <163925564+nvda-mesharma@users.noreply.github.com>

538b4630

docs: add to documentation for Kubernetes deployments, devcontainer improvements (#498) · 441846de

hhzhang16 authored Apr 10, 2025

441846de

10 Apr, 2025 14 commits
- feat: save `dynamo serve` local state for planner and cleanups (#560) · 3136b716
  ishandhanani authored Apr 10, 2025
  
  3136b716
- docs: update README with instructions for build & install in a conda env (#478) · 07f2f0ad
  Venkat Raman authored Apr 11, 2025
```
Signed-off-by: Venkat Raman <vraman2811@gmail.com>
```
  07f2f0ad
- fix: wheel for api-store should not be built and installed (#584) · 75afd7c4
  mohammedabdulwahhab authored Apr 10, 2025
  
  75afd7c4
- fix: fix dynamoNimDeployment status (#551) · 044e12e1
  julienmancuso authored Apr 10, 2025
  
  044e12e1
- fix: update yum install in wheel-builder image (#605) · 0ff6f53d
  Anant Sharma authored Apr 10, 2025
  
  0ff6f53d
- chore: update ai-dynamo-vllm wheel version (#598) · ff30778c
  Anant Sharma authored Apr 10, 2025
  
  ff30778c
- fix: set env vars before worker spawn (#583) · dee80d18
  ishandhanani authored Apr 10, 2025
  
  dee80d18
- docs: update dynamo serve trtllm agg example yaml files (#600) · 34be4418
  Ziqi Fan authored Apr 10, 2025
  
  34be4418
- fix: frontend now cleans up model from llmctl (#588) · bb4e819c
  Alec authored Apr 10, 2025
  
  bb4e819c
- fix: correct framework validation logic (#595) · a40aae9e
  Zhan Lu authored Apr 11, 2025
  
  a40aae9e
- chore: use latest nixl for docker builds (#593) · 6486dd53
  Anant Sharma authored Apr 10, 2025
  
  6486dd53
- fix: shellcheck errors (#298) · aa83c8aa
  Carsten Csiky authored Apr 10, 2025
```
Co-authored-by: Meenakshi Sharma <163925564+nvda-mesharma@users.noreply.github.com>
```
  aa83c8aa
- chore: check prefix caching while using kv router (#592) · 7cf75628
  tlipoca9 authored Apr 10, 2025
```
Neelay approved merge
```
  7cf75628
- feat: Add POST deployments endpoint to api-store service in Dynamo cloud (#582) · 7662de1c
  mohammedabdulwahhab authored Apr 09, 2025
```
Co-authored-by: Hannah Zhang <hannahz@nvidia.com>
Co-authored-by: Julien Mancuso <jmancuso@nvidia.com>
Co-authored-by: mabdulwahhab <mabdulwahhab@nvidia.com>
```
  7662de1c