Commits · 8ebfd1e4e7f12c69a16a95c38c4f387278a166eb · OpenDAS / dynamo

27 Jan, 2026 1 commit
- fix: Update the vllm docker image to use the cuda sampler rather than the pytorch one (#5613) · f9858193
  Kyle McGill authored Jan 26, 2026
  
  f9858193
24 Jan, 2026 1 commit

chore(deps): bump vLLM to 0.14.0 (#5593) · 50f1e0e1

Alec authored Jan 23, 2026


Signed-off-by: alec-flowers <aflowers@nvidia.com>
Signed-off-by: Alec Flowers <aflowers@nvidia.com>
Signed-off-by: Alec <35311602+alec-flowers@users.noreply.github.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

50f1e0e1

23 Jan, 2026 1 commit
- feat: GPU Memory Service (#5286) · 30c6228b
  Schwinn Saereesitthipitak authored Jan 23, 2026
```
Signed-off-by: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com>
```
  30c6228b
22 Jan, 2026 1 commit

ci: split vllm venv COPY into parallel layers for faster pulls (#5494) · b31b5b56

Alec authored Jan 22, 2026


Signed-off-by: alec-flowers <aflowers@nvidia.com>
Signed-off-by: Alec <35311602+alec-flowers@users.noreply.github.com>

b31b5b56

14 Jan, 2026 1 commit

refactor: remove "dev" stage from Dockerfile.* and centralize them into Dockerfile.dev (#5050) · 4816d639

Keiven C authored Jan 13, 2026


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

4816d639

13 Jan, 2026 1 commit
- chore: Bump CUDA to 12.9.1 for vllm container (#5397) · 58a061f4
  Dmitry Tokarev authored Jan 13, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  58a061f4
12 Jan, 2026 2 commits
- chore: explicitly install GPG package in containers (#5374) · 16451f48
  Tushar Sharma authored Jan 12, 2026
```
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
```
  16451f48
- fix: NIXL CUDA12 + CUDA13 build (#5000) · ae03c857
  Erez Zarum authored Jan 12, 2026
```
Signed-off-by: Erez Zarum <erezz@amazon.com>
```
  ae03c857
06 Jan, 2026 1 commit

fix: update vLLM to 0.13.0 with API compatibility fixes (#5222) · a1333a8d

Alec authored Jan 06, 2026


Signed-off-by: Vasilis Vagias <vvagias@nvidia.com>
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Vasilis Vagias <vvagias@nvidia.com>

a1333a8d

05 Jan, 2026 1 commit
- fix: Pin GNU gcc version to 14 to build CUDA (#5145) · 4cfd603c
  jh-nv authored Jan 05, 2026
```
Signed-off-by: Jie Hao <jihao@nvidia.com>
Co-authored-by: Yan Ru Pei <yanrpei@gmail.com>
```
  4cfd603c
02 Jan, 2026 1 commit
- chore: update all copyright headers in repo to 2026 (#5130) · cf433e68
  Tushar Sharma authored Jan 02, 2026
```
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
```
  cf433e68
24 Dec, 2025 1 commit
- feat: KVBM Object Support - add obj plugin deps (#5059) · 22199857
  Patrick authored Dec 23, 2025
```
Signed-off-by: Patrick Riel <priel@nvidia.com>
```
  22199857
20 Dec, 2025 1 commit

fix: dev container to be able to compile after base image change (#5049) · 7813e38b

Keiven C authored Dec 20, 2025


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

7813e38b

18 Dec, 2025 3 commits

feat: VLLM + CUDA 13 (#4997) · 7a3b15e6

Dmitry Tokarev authored Dec 18, 2025


Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

7a3b15e6

fix: ffmpeg legal alignment (#5002) · e36b7e7a
milesial authored Dec 18, 2025
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
e36b7e7a

feat: Libfabric support (#4407) · 00b38ded

Joe Chandler authored Dec 17, 2025


Signed-off-by: Joe Chandler <jchandler@glia-ai.com>
Co-authored-by: Meenakshi Sharma <163925564+nvda-mesharma@users.noreply.github.com>

00b38ded

16 Dec, 2025 1 commit
- feat: video decoder in the frontend (#4719) · 74fcd4a9
  milesial authored Dec 16, 2025
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  74fcd4a9
11 Dec, 2025 1 commit

ci: Fixing sccache behavior (#4866) · 242a4d5b

Dillon Cullinan authored Dec 11, 2025


Signed-off-by: Dillon Cullinan <dcullinan@nvidia.com>
Signed-off-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>

242a4d5b

10 Dec, 2025 2 commits

fix: sccache compiler launcher errors when sccache is disabled (#4846) · cc2ee1ed

Keiven C authored Dec 10, 2025


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

cc2ee1ed

ci: OPS-2136: Setup caching for docker build (#4535) · c9e445a9

Dillon Cullinan authored Dec 09, 2025

Signed-off-by: Dillon Cullinan <dcullinan@nvidia.com>
Signed-off-by: Dillon Cullinan <dillon-cullinan@users.noreply.github.com>
Co-authored-by: Dillon Cullinan <dillon-cullinan@users.noreply.github.com>

c9e445a9

08 Dec, 2025 1 commit

refactor: update Dockerfiles to use group writes for development, saving build time (#4657) · 0dd51694

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>

0dd51694

05 Dec, 2025 1 commit

ci: Adding nightly pipeline workflow (#4204) · a9078ed0

Pavithra Vijayakrishnan authored Dec 05, 2025


Signed-off-by: pvijayakrish <pvijayakrish@nvidia.com>
Signed-off-by: Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>

a9078ed0

04 Dec, 2025 1 commit

chore: bump vLLM to 0.12.0 (#4736) · d7c11b65

Karen Chung authored Dec 03, 2025


Signed-off-by: alec-flowers <aflowers@nvidia.com>
Signed-off-by: Karen Chung <karenc@nvidia.com>
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: jthomson04 <jwillthomson19@gmail.com>

d7c11b65

03 Dec, 2025 3 commits
- fix: copy wheel meta files in vllm dev stage for editable install (#4738) · 845a06b3
  Anant Sharma authored Dec 03, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  845a06b3
- chore: bump vLLM to 0.11.2 (#4476) · 60feb955
  Karen Chung authored Dec 03, 2025
  
  60feb955
- build: reorder docker layers to maximize layer cache hits (#4468) · dab2de67
  Anant Sharma authored Dec 03, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
Co-authored-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
```
  dab2de67
02 Dec, 2025 1 commit

fix: pin sniffio dependency (#4665) · 9fb5f03a

Biswa Panda authored Dec 01, 2025


Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: PeaBrane <yanrpei@gmail.com>

9fb5f03a

26 Nov, 2025 1 commit
- chore(container): clean up Dockerfile.{sglang,trtllm,vllm} and build.sh (#4569) · f33fdd52
  Keiven C authored Nov 25, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  f33fdd52
23 Nov, 2025 1 commit
- feat: Better cublas support in vLLM container. (#4514) · f0ca16f0
  jthomson04 authored Nov 23, 2025
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
```
  f0ca16f0
21 Nov, 2025 1 commit
- chore: split frontend + runtime launch message to accurately represent container purpose (#4537) · f2769d88
  Tushar Sharma authored Nov 21, 2025
```
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
Co-authored-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
```
  f2769d88
18 Nov, 2025 1 commit
- fix: Fix cublas and cublasLt symlinks in vLLM runtime container (#4421) · 1a27649c
  jthomson04 authored Nov 17, 2025
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
```
  1a27649c
13 Nov, 2025 1 commit

fix: TRTLLM build from source not repsecting the wheel installation directory (#4241) · 02763376

Kyle McGill authored Nov 13, 2025


Signed-off-by: Kyle McGill <101670481+nv-kmcgill53@users.noreply.github.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>

02763376

10 Nov, 2025 1 commit
- build: add non root user for dynamo backend runtime containers (#3935) · 6f708832
  Anant Sharma authored Nov 10, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  6f708832
31 Oct, 2025 1 commit

chore: KVBM pip wheel (#3826) · 6afa679c

Richard Huo authored Oct 31, 2025


Signed-off-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>

6afa679c

20 Oct, 2025 1 commit
- feat: python package build with abi (cross py3.10+) (#3571) · af7b73c0
  Michael Feil authored Oct 20, 2025
```
Signed-off-by: michaelfeil <me@michaelfeil.eu>
```
  af7b73c0
17 Oct, 2025 1 commit
- refactor: remove redundant COPY in dev stage of framework Dockerfiles (#3690) · e2d66dba
  Keiven C authored Oct 17, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  e2d66dba
16 Oct, 2025 1 commit
- fix: git lfs support is erratic with uv so set env var to force it (#3671) · 34fc9693
  Harrison Saturley-Hall authored Oct 16, 2025
```
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
```
  34fc9693
15 Oct, 2025 1 commit
- fix: aarch64 path to use cu129 (#3624) · a6ac22e6
  Alec authored Oct 15, 2025
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
```
  a6ac22e6
14 Oct, 2025 1 commit

feat: update benchmarking script to use aiperf (#3306) · de3ca70b

Biswa Panda authored Oct 13, 2025


Signed-off-by: Biswa Panda <biswa.panda@gmail.com>
Signed-off-by: lkomali <lkomali@nvidia.com>
Co-authored-by: lkomali <lkomali@nvidia.com>
Co-authored-by: Harshini Komali <157742537+lkomali@users.noreply.github.com>

de3ca70b

12 Oct, 2025 1 commit
- chore: bump vllm to 0.11.0 (#3422) · 90dc7589
  Alec authored Oct 12, 2025
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
```
  90dc7589