Commits · 82577b06889f1d3a77c1af2eec8153b923d2d107 · OpenDAS / dynamo · GitLab

11 Dec, 2025 6 commits
- fix: relax pydantic requirements (#4865) · 2ef0f5fb
  Dmitry Tokarev authored Dec 11, 2025
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  2ef0f5fb
- test: graceful shutdown for tcp req plane (#4883) · 5e96c9a8
  Biswa Panda authored Dec 11, 2025
  
  5e96c9a8
- feat: add cached tokens prometheus metric (#4534) · f8bb53c0
  Vladislav Nosivskoy authored Dec 11, 2025
```
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  f8bb53c0
- feat: include ttft and total request time in nvext (engine-agnostic) (#4880) · 2845aa1f
  Yan Ru Pei authored Dec 10, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Signed-off-by: Yan Ru Pei <yanrpei@gmail.com>
Co-authored-by: Keiven C <213854356+keivenchang@users.noreply.github.com>
```
  2845aa1f
- test: Ensure Request Cancellation, Migration, Rejection Work with TCP transport (#4875) · 00f8615e
  Jacky authored Dec 10, 2025
```
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
```
  00f8615e
- fix: worker to graceful shutdown after finishing in-flight requests (#4838) · c8845b41
  Hongkuan Zhou authored Dec 10, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: Biswa Panda <biswa.panda@gmail.com>
```
  c8845b41
10 Dec, 2025 4 commits
- fix: Don't set min_tokens when ignore_eos is true (#4872) · 664b458a
  jthomson04 authored Dec 10, 2025
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
```
  664b458a
- feat: non blocking radix snapshot upload (#4839) · c7ad78f3
  Yan Ru Pei authored Dec 10, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  c7ad78f3
- feat: KVBM V2 optimized bounce buffer transfer + benchmark (#3947) · 01819b87
  jthomson04 authored Dec 09, 2025
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
```
  01819b87
- feat: DeepSeek V3.2 tool calling support (#4822) · 6d091bf3
  Vladislav Nosivskoy authored Dec 10, 2025
```
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: Ayush Agarwal <ayushag@nvidia.com>
```
  6d091bf3
09 Dec, 2025 10 commits
- feat: nixl_connect: Improve Concurrency Support (#4433) · 96fe63fe
  J Wyman authored Dec 09, 2025
```
Signed-off-by: J Wyman <jwyman@nvidia.com>
```
  96fe63fe
- chore: cleanups of passing around prefill and decode worker ids (#4829) · 1e5b20b2
  Yan Ru Pei authored Dec 09, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  1e5b20b2
- fix: backend error serialization and add HTTP status code detection (#4786) · 065f466e
  Tzu-Ling Kan authored Dec 09, 2025
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  065f466e
- chore(pipeline): Move migration outside of backend (#4823) · d5f425ab
  Graham King authored Dec 09, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  d5f425ab
- feat: Disable health checks by default; auto-enable in K8s via operator (#4804) · 7c15166d
  Tzu-Ling Kan authored Dec 09, 2025
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  7c15166d
- feat: add tool_choice support (#4722) · 5585f803
  Vladislav Nosivskoy authored Dec 09, 2025
```
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
```
  5585f803
- feat: Change health check log level from info to debug (#4818) · 1f9b69b0
  Tzu-Ling Kan authored Dec 09, 2025
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  1f9b69b0
- fix: add timeout to tests before lora to unblock (#4808) · 1e37c103
  Keiven C authored Dec 08, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  1e37c103
- fix: have frontend populate "stop" field in OpenAI request (#4782) · e6de33f8
  Page authored Dec 08, 2025
  
  e6de33f8
- fix: Fix warning messages with healthcheck (#4793) · bd4366d0
  jthomson04 authored Dec 08, 2025
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
```
  bd4366d0
08 Dec, 2025 2 commits
- chore: de-spaghetti mocker scheduler (#4789) · 377711d3
  Yan Ru Pei authored Dec 08, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  377711d3
- chore: jamba based parsers (#4776) · c9fad85c
  Ayush Agarwal authored Dec 08, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  c9fad85c
06 Dec, 2025 1 commit
- test: add timeout for lora utils tests (#4781) · 5588d770
  Biswa Panda authored Dec 05, 2025
  
  5588d770
05 Dec, 2025 3 commits
- fix: use channel to avoid race condition from async nats registration task (#4758) · 501ef021
  Biswa Panda authored Dec 05, 2025
  
  501ef021
- feat: Add python-configurable engine routes for sglang profiling (#4617) · 3bc129dc
  William Arnold authored Dec 05, 2025
```
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
```
  3bc129dc
- build: Enable frontend decoding (media-nixl) in regular dynamo builds (#4618) · 76f4bc83
  KrishnanPrash authored Dec 05, 2025
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  76f4bc83
04 Dec, 2025 6 commits
- fix: skip HuggingFace download for non-llms (#4686) · 118323f2
  Neal Vaidya authored Dec 04, 2025
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
```
  118323f2
- refactor: remove legacy NATS metrics and stats_handler (#4680) · 00b64ae0
  Keiven C authored Dec 04, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  00b64ae0
- fix: vLLM xfer bug (#4745) · 173201f5
  Alec authored Dec 04, 2025
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
```
  173201f5
- fix: parallel tool call indices in streaming (#4723) · 8601ccdb
  Vladislav Nosivskoy authored Dec 04, 2025
```
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
```
  8601ccdb
- feat: Turn on canary health check by default (#4368) · d5800311
  Tzu-Ling Kan authored Dec 03, 2025
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  d5800311
- chore: no need to arc wrap client (#4741) · 5b24b429
  Yan Ru Pei authored Dec 03, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  5b24b429
03 Dec, 2025 6 commits
- chore: bump vLLM to 0.11.2 (#4476) · 60feb955
  Karen Chung authored Dec 03, 2025
  
  60feb955
- chore: Arc wrap prometheus_registry in MetricsRegistry (#4677) · c5e8c4c2
  Yan Ru Pei authored Dec 03, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  c5e8c4c2
- fix: Updates CUDA fatbin for KVBM (#4700) · 991d8c72
  Olga Andreeva authored Dec 03, 2025
```
Signed-off-by: Olga Andreeva <oandreeva@nvidia.com>
```
  991d8c72
- feat: add Kserve readiness endpoint support: ServerLive / ServerReady / ModelReady (#4708) · d90dc39d
  GuanLuo authored Dec 03, 2025
```
Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  d90dc39d
- test: remove redundant mocker e2e test in rust (#4720) · 77841e7b
  Yan Ru Pei authored Dec 03, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  77841e7b
- fix: integration test failures. Support DYN_SYSTEM_PORT=0 for random port... · 3cad926e
  Keiven C authored Dec 02, 2025
```
fix: integration test failures. Support DYN_SYSTEM_PORT=0 for random port binding, and update etcd test (#4687)
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  3cad926e
02 Dec, 2025 2 commits

feat: Extend the KV Event Consolidator to support TensorRT-LLM (#4533) · 6067c59d
Kris Hung authored Dec 02, 2025
```
Signed-off-by: krishung5 <krish@nvidia.com>
```
6067c59d

fix: ModelDeploymentCard obtains full set of eos_token_ids by taking union... · 4ace4c85

GuanLuo authored Dec 02, 2025

fix: ModelDeploymentCard obtains full set of eos_token_ids by taking union from different files (#3192)
Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>

4ace4c85