Commits · 673822ea931352cebe5d6e49a9b66f66a8f1d272 · OpenDAS / dynamo

23 Feb, 2026 2 commits
- fix(chrek): fix CI errors and replace SIGUSR2 with SIGKILL on checkpoint failure (#6478) · 673822ea
  Schwinn Saereesitthipitak authored Feb 23, 2026
  
  673822ea
- feat: Backend accept new requests during shutdown grace period (#6093) · ea86df29
  jh-nv authored Feb 22, 2026
```
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
Co-authored-by: Jacky <18255193+kthui@users.noreply.github.com>
```
  ea86df29
22 Feb, 2026 3 commits

feat: add --headless mode for multi-node TP/PP in dynamo.vllm (#6204) · 4ebb244b

Alec authored Feb 22, 2026


Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

4ebb244b

fix: gracefully skip NIXL UCX tests when backend unavailable (#6484) · d3ee09d7

Alec authored Feb 22, 2026


Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

d3ee09d7

fix: add pre_merge markers to vLLM unit tests (#6482) · a9568455

Alec authored Feb 22, 2026


Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

a9568455

21 Feb, 2026 3 commits
- fix: Multimodal flag was ignored for TRTLLM (#6468) · 8d30cd45
  William Zhang authored Feb 21, 2026
```
* Why?

Commit `5a67b246` refactored configs for the TRTLLM backend, breaking
`--modality multimodal`.

* What?

This commit fixes this bug, and adds a unit test verified to fail
without it.
```
  8d30cd45
- feat: Remove public uses of CancellationToken (#6405) · 42d69805
  Tzu-Ling Kan authored Feb 20, 2026
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  42d69805
- feat(chrek): external restore, signal-based IPC, and package refactor (#6286) · bb8fc8a4
  Schwinn Saereesitthipitak authored Feb 20, 2026
```
Co-authored-by: Dan Feigin <dfeigin@nvidia.com>
```
  bb8fc8a4
20 Feb, 2026 24 commits
- Run Fault Tolerance test jobs only in Nightly pipeline (not in post-m… (#6462) · c8423b57
  Dmitry Tokarev authored Feb 20, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  c8423b57
- test: add TensorRT-LLM multimodal EPD test for nightly CI (#6193) · da7d3e9e
  knarangN authored Feb 20, 2026
```
Signed-off-by: Kavita Narang <knarang@nvidia.com>
```
  da7d3e9e
- feat(frontend): Reduce Python-side overhead in the vLLM chat path (#6437) · f91b42b9
  Graham King authored Feb 20, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  f91b42b9
- fix: reintroduce helm docs autogeneration (#6459) · fd839b8d
  Julien Mancuso authored Feb 20, 2026
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  fd839b8d
- fix: Fix dev container build (#6455) · a798e08c
  William Zhang authored Feb 20, 2026
```
There were 2 bugs prior to this commit when building a TRTLLM dev
container:

- template rendering bug
- CUDA compatibility layer

The `nvidia_entrypoint.sh` script should render the second completely
unnecessary.
```
  a798e08c
- fix: Docker push retries (#6456) · 6c698b8b
  Dmitry Tokarev authored Feb 20, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  6c698b8b
- chore: cargo machete - remove unused dependencies (#6453) · 7a6283e9
  Ryan Olson authored Feb 20, 2026
```
Signed-off-by: Ryan Olson <rolson@nvidia.com>
```
  7a6283e9
- refactor(mocker): modularize into common/scheduler/kv_manager/cache (#6440) · 9b2e8f3d
  Yongming Ding authored Feb 20, 2026
```
Signed-off-by: Yongming Ding <yongmingd@nvidia.com>
```
  9b2e8f3d
- feat: Configurable Request Cancellation abort passage to TRT-LLM (#6445) · 41d7d549
  Jacky authored Feb 20, 2026
```
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
```
  41d7d549
- feat: interleaved thinking support in reasoning parser (#6422) · d82b0050
  MatejKosec authored Feb 20, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  d82b0050
- fix: vllm omni image perf fix (#6451) · 7409bd3a
  Ayush Agarwal authored Feb 20, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  7409bd3a
- fix(recipes): change componentType from "main" to "worker" for TRT-LL… (#5788) · edc0d4b6
  mwieczorek authored Feb 20, 2026
  
  edc0d4b6
- fix: use diff temp dir for pytest (#6449) · 2baafc2a
  Dmitry Tokarev authored Feb 20, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  2baafc2a
- fix: increase lychee timeouts and retries (#6444) · 16cec713
  Dmitry Tokarev authored Feb 20, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  16cec713
- chore: remove mechanism to disable webhooks (#6441) · f385661a
  Julien Mancuso authored Feb 20, 2026
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  f385661a
- feat: add embedding cache to pd worker (#6061) · c82fe888
  Qi Wang authored Feb 20, 2026
  
  c82fe888
- feat: Add v1beta1 DGDR API with conversion framework (#6352) · ebc61637
  hhzhang16 authored Feb 19, 2026
```
Signed-off-by: Jont828 <jt572@cornell.edu>
Signed-off-by: Hongkuan Zhou <hongkuanz@nvidia.com>
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Co-authored-by: Jont828 <jt572@cornell.edu>
```
  ebc61637
- feat: default kv-events-config to empty (align with vLLM defaults) (#6404) · 7bbacce1
  Alec authored Feb 19, 2026
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  7bbacce1
- chore: unify filesystem usage across all frameworks and workers (#6391) · d6c49779
  Ayush Agarwal authored Feb 19, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  d6c49779
- feat: vllm omni text to video generation pipeline (#6104) · 6dd3ce2e
  Ayush Agarwal authored Feb 19, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  6dd3ce2e
- feat: e2e mm aware kv cache routing support for trtllm backend (#5480) · 23de4e86
  zhongdaor-nv authored Feb 19, 2026
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
Signed-off-by: zhongdaor-nv <zhongdaor@nvidia.com>
Signed-off-by: Zhongdao Ren <zhongdaor@zhongdaor-mlt.client.nvidia.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Zhongdao Ren <zhongdaor@zhongdaor-mlt.client.nvidia.com>
```
  23de4e86
- feat: TRT-LLM multimodal preprocessor with backend media decoding (#5910) · 8a098a66
  Michal Guzek authored Feb 19, 2026
```
Signed-off-by: Michal Guzek <mguzek@nvidia.com>
```
  8a098a66
- docs: fix 14 broken links detected by lychee CI (#6438) · 9bdc8b73
  dagil-nvidia authored Feb 19, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
```
  9bdc8b73
- fix: Fix async pytests - added missing marker (#6439) · 121d8050
  Dmitry Tokarev authored Feb 19, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  121d8050
19 Feb, 2026 8 commits
- feat: add examples for multimodal loras (#6400) · a28c5f3a
  Biswa Panda authored Feb 19, 2026
  
  a28c5f3a
- feat: resolve lora request for multimodal workers (#6399) · 026f361d
  Biswa Panda authored Feb 19, 2026
  
  026f361d
- chore: self contained EPP Dockerfile (#6412) · bc320806
  Ran Rubin authored Feb 20, 2026
  
  bc320806
- fix: deploy-operator - remove unused pull secret, use helm install --debug (#6434) · 2316516e
  Dmitry Tokarev authored Feb 19, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  2316516e
- feat: Add runtime.endpoint() method to eliminate namespace chaining (#6386) · 0ce3461a
  Tzu-Ling Kan authored Feb 19, 2026
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  0ce3461a
- test: add vllm audio tests to nightly ci pipeline (#6392) · 6f4b33f7
  knarangN authored Feb 19, 2026
```
Signed-off-by: Kavita Narang <knarang@nvidia.com>
```
  6f4b33f7
- feat: add model field to multimodal protocol for LoRA identity (#6382) · 4ba48b79
  Biswa Panda authored Feb 19, 2026
  
  4ba48b79
- fix: disable etcd subchart by default (#6329) · 46d9f448
  mohammedabdulwahhab authored Feb 19, 2026
```
Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
```
  46d9f448