Commits · cdfd70f0fed86fe773a2acd125edc340635163e2 · OpenDAS / dynamo

"tests/vscode:/vscode.git/clone" did not exist on "a665886a420adc2a24de3834b010ff27e01e9e72"

09 Oct, 2025 1 commit
- feat: changing SIGKILL to SIGINT for graceful shutdown (#3513) · cdfd70f0
  Tzu-Ling Kan authored Oct 08, 2025
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  cdfd70f0
08 Oct, 2025 18 commits
- fix: remove _version import in config_dump (#3502) · 9b5bab72
  William Arnold authored Oct 08, 2025
```
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
```
  9b5bab72
- feat: Add OpenAPI routes to serve HTTP server API documentation (#3480) · ef04a086
  Ryan McCormick authored Oct 08, 2025
  
  ef04a086
- feat: enable KVBM to support PD disagg in Dynamo vLLM (#3352) · 9975cb9f
  Ziqi Fan authored Oct 08, 2025
```
Signed-off-by: Ziqi Fan <ziqif@nvidia.com>
```
  9975cb9f
- chore: Remove llama.cpp engine (#3499) · 0aa0768f
  Graham King authored Oct 08, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  0aa0768f
- fix: update dynamo namespace env var usage (#3477) · 552146f2
  Biswa Panda authored Oct 08, 2025
  
  552146f2
- ci: disable gitlab sdk pipeline (#3494) · 466b1993
  Anant Sharma authored Oct 08, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  466b1993
- feat: prefill routing for trtllm (#3471) · f3987f6c
  Yan Ru Pei authored Oct 08, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  f3987f6c
- feat: DIS-678 kvbm modularity: standalone metrics endpoint (#3433) · cf83794a
  Richard Huo authored Oct 08, 2025
```
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
```
  cf83794a
- fix: frontend component handles graceful shutdown (#3481) · 2d59861e
  Thomas Montfort authored Oct 08, 2025
  
  2d59861e
- chore: Upgrade mistralrs (#3490) · 07207a1b
  Graham King authored Oct 08, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  07207a1b
- docs: backend engines do not need to emit deterministic blocks (#3484) · 3aeae151
  Yan Ru Pei authored Oct 08, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  3aeae151
- fix: minor robustness improvement for datagen analyze (#3483) · ec438f8c
  Yan Ru Pei authored Oct 08, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  ec438f8c
- fix: update distroless go container for operator to fix openssl (#3486) · 0a5df130
  Harrison Saturley-Hall authored Oct 08, 2025
```
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
```
  0a5df130
- chore: Remove GGUF support (#3488) · 1b1265e6
  Graham King authored Oct 08, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  1b1265e6
- feat: add Python MetricsRegistry Python metrics registration (#3341) · 0c4c4d1d
  Keiven C authored Oct 07, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  0c4c4d1d
- fix: dynamo.common import failing on non-editable installs (#3478) · 8c9f3616
  William Arnold authored Oct 07, 2025
```
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
```
  8c9f3616
- docs: added example for a frontend shared across multiple models (#3008) · 13bf5d91
  Maksim Khadkevich authored Oct 07, 2025
```
Signed-off-by: Maksim Khadkevich <mkhadkevich@nvidia.com>
```
  13bf5d91
- feat: a script to convert BurstGPT to mooncake format (#3479) · 87825339
  Hongkuan Zhou authored Oct 07, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  87825339
07 Oct, 2025 21 commits
- feat: pre-deployment profiling automatically generates and deploys optimized... · 83e259a7
  Hongkuan Zhou authored Oct 07, 2025
```
feat: pre-deployment profiling automatically generates and deploys optimized DGD with planner (#3441)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  83e259a7
- ci: Removed pre-merge marker from test_vllm_unit.py (#3474) · 43ea602a
  KrishnanPrash authored Oct 07, 2025
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  43ea602a
- fix: Make planner VirtualConnectorClient also use v1/ prefix. (#3468) · bdad6f1a
  Graham King authored Oct 07, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  bdad6f1a
- chore: update guide for reasoning & tool calling parser with gpt-oss on trtllm (#3262) · 55f7e637
  zhongdaor-nv authored Oct 07, 2025
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
```
  55f7e637
- fix: update ETCD image (#3457) · b1b7c50c
  Julien Mancuso authored Oct 07, 2025
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  b1b7c50c
- feat: add startup order for multinode TRTLLM (#3462) · 55de76b6
  Julien Mancuso authored Oct 07, 2025
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  55de76b6
- build: scan source dir for components in hatch build (#3348) · 96a6dcda
  Anant Sharma authored Oct 07, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  96a6dcda
- fix: remove warnings in build process (#3463) · b51b6e57
  Anant Sharma authored Oct 07, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  b51b6e57
- feat: Connect DYN_LOG level to TLLM_LOG_LEVEL (#3451) · 68bbe8a9
  Tanmay Verma authored Oct 07, 2025
```
Signed-off-by: Tanmay Verma <tanmay2592@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
```
  68bbe8a9
- perf: Improve performance of snapshot using a reverse lookup from block -> external hash (#3370) · 11694273
  blarson-b10 authored Oct 07, 2025
```
Signed-off-by: Brian Larson <brian.larson@baseten.co>
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: PeaBrane <yanrpei@gmail.com>
```
  11694273
- refactor: rename dynamo_check.py to sanity_check.py (#3423) · 1ddb9b0c
  Keiven C authored Oct 07, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  1ddb9b0c
- feat: add flag for dumping dynamo engine config and environment (#3286) · 2e1f5076
  William Arnold authored Oct 07, 2025
```
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
```
  2e1f5076
- docs: Update trtllm multinode multimodal docs (#3369) · 04aafa9a
  Indrajit Bhosale authored Oct 07, 2025
```
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
```
  04aafa9a
- docs: move doc build dependencies to pyproject.toml (#3453) · ff7d43d0
  Neal Vaidya authored Oct 07, 2025
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
```
  ff7d43d0
- chore: add e2e test for reasoning_effort for gpt-oss model (#3421) · 89e7dab2
  zhongdaor-nv authored Oct 07, 2025
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
Signed-off-by: zhongdaor-nv <zhongdaor@nvidia.com>
```
  89e7dab2
- feat: Deployment for EPP as a static library (#3314) · 6d62fc74
  atchernych authored Oct 07, 2025
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  6d62fc74
- feat: use generic image and use single node for oss-gpt-120b recipe (#3454) · af7a41c3
  Biswa Panda authored Oct 07, 2025
  
  af7a41c3
- ci: Adding Unit Tests for vLLM (--custom-jinja-template) (#3362) · ff625465
  KrishnanPrash authored Oct 07, 2025
  
  ff625465
- feat(etcd): Version the etcd keys (#3458) · a5371bfc
  Graham King authored Oct 07, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  a5371bfc
- feat: add github actions metrics upload for build image jobs (#3260) · 31b78e96
  nv-nmailhot authored Oct 07, 2025
```
Signed-off-by: nv-nmailhot <nmailhot@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>

Covers queue time and duration metrics
```
  31b78e96
- chore(discovery): Watch/publish ModelDeploymentCard instead of ModelEntry (#3350) · 81162dfe
  Graham King authored Oct 07, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  81162dfe