Commits · fcc42624a36ab2aaa71c0a8ddf3ec09e5cd12987 · OpenDAS / dynamo · GitLab

01 Oct, 2025 8 commits
- feat: Add vLLM compilation cache to Dynamo Operator (#3257) · fcc42624
  Michael Shin authored Oct 01, 2025
```
Signed-off-by: Michael Shin <michaelshin@users.noreply.github.com>
```
  fcc42624
- feat: Using ai-perf for k8 FT tests. (#3289) · 02c822d6
  Tzu-Ling Kan authored Sep 30, 2025
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  02c822d6
- feat: Add --custom-jinja-template argument to pass a custom chat template for TRTLLM (#3332) · b5782fcd
  KrishnanPrash authored Sep 30, 2025
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  b5782fcd
- feat: make prefill router general (#3329) · 9b9536d0
  Yan Ru Pei authored Sep 30, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  9b9536d0
- chore: enable gpt oss reasoning to work with text and tokens (#3321) · 3d2d7e47
  Ayush Agarwal authored Sep 30, 2025
```
Signed-off-by: Ayush Agarwal <ayushag@nvidia.com>
```
  3d2d7e47
- refactor: standardize Prometheus metric naming conventions (part 1) (#3035) · f4a3a6b6
  Keiven C authored Sep 30, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  f4a3a6b6
- fix: update post-create.sh for current build system and fix unbound variables (#3304) · cab23f21
  Keiven C authored Sep 30, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  cab23f21
- feat: add Context class to Python type stubs (#3327) · af4c0cad
  Keiven C authored Sep 30, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  af4c0cad
30 Sep, 2025 24 commits
- feat: Add --custom-jinja-template argument to pass a custom chat template for SGLang (#3165) · f95ba894
  KrishnanPrash authored Sep 30, 2025
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
Signed-off-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  f95ba894
- fix: allow tolerations and affinity to be set in jobs that run during helm install (#3324) · 65401d75
  Julien Mancuso authored Sep 30, 2025
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  65401d75
- fix: Edge cases for Parallel tool calling (#3283) · 9088e1b5
  Elyas Mehtabuddin authored Sep 30, 2025
```
Signed-off-by: Elyas Mehtabuddin <emehtabuddin@nvidia.com>
```
  9088e1b5
- fix: fix the lmcache args in the agg_lmcache.sh script (#3325) · 1a6eb099
  Richard Huo authored Sep 30, 2025
```
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
```
  1a6eb099
- chore: update slurm scrips for better warmup and bump sgl version (#3291) · 0ab6bc2b
  ishandhanani authored Sep 30, 2025
  
  0ab6bc2b
- refactor: Simplify TRT-LLM request abort calling logic (#3296) · 87190db0
  Jacky authored Sep 30, 2025
```
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
```
  87190db0
- feat: add audit logging for chat completions (#3062) · 56d20f53
  ryan-lempka authored Sep 30, 2025
```
Signed-off-by: Ryan Lempka <rlempka@nvidia.com>
```
  56d20f53
- feat: python add abi compatability for cross-platform builds + add a unit test... · 5b457b70
  Michael Feil authored Sep 30, 2025
```
feat: python add abi compatability for cross-platform builds + add a unit test to HttpServer (#3044)
Signed-off-by: michaelfeil <me@michaelfeil.eu>
Signed-off-by: Michael Feil <63565275+michaelfeil@users.noreply.github.com>
Signed-off-by: root <root@michaelfeil2-dev-pod-b200-0.michaelfeil2-dev-pod-b200.baseten.svc.cluster.local>
Signed-off-by: root <root@michaelfeildns-dev-pod-h100-0.michaelfeildns-dev-pod-h100.baseten.svc.cluster.local>
Co-authored-by: root <root@michaelfeil2-dev-pod-b200-0.michaelfeil2-dev-pod-b200.baseten.svc.cluster.local>
Co-authored-by: root <root@michaelfeildns-dev-pod-h100-0.michaelfeildns-dev-pod-h100.baseten.svc.cluster.local>
```
  5b457b70
- chore: Add Key abstraction in our KeyValueStore (#3322) · 50cdae5f
  Graham King authored Sep 30, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  50cdae5f
- fix: update ecs deployment example (#3284) · cf3ac5b6
  Neal Vaidya authored Sep 30, 2025
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
```
  cf3ac5b6
- fix: Fix gpt_oss_parser last_content_delta to accumulate tokens + add regression test (#3301) · 95042f82
  zhongdaor-nv authored Sep 30, 2025
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
Signed-off-by: zhongdaor-nv <zhongdaor@nvidia.com>
Co-authored-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
```
  95042f82
- fix: python bindings for router should register to etcd as well (#3302) · d354763c
  Yan Ru Pei authored Sep 30, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  d354763c
- fix: Install right versions of the dependencies for tensorrtllm (#3218) · c265cd67
  Tanmay Verma authored Sep 30, 2025
  
  c265cd67
- fix: KV Router bindings docs (#3308) · f0041782
  Yan Ru Pei authored Sep 30, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  f0041782
- docs: remove base container as it varies, note no support trtllm py 3.11 (#3312) · 889e7f4b
  Harrison Saturley-Hall authored Sep 30, 2025
```
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
```
  889e7f4b
- fix: fail fast custom template not found & more verbose vllm engine error (#3278) · 97fee502
  Chia-Wei authored Sep 30, 2025
```
Signed-off-by: Chia-Wei Chen <cchen562@wisc.edu>
```
  97fee502
- feat: add Python const for Prometheus metric names (#3244) · cacac9b9
  Keiven C authored Sep 30, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  cacac9b9
- refactor: standardize HF_CACHE to HF_HOME across codebase (use Hugging Face convention) (#3310) · 481bf395
  Keiven C authored Sep 30, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  481bf395
- chore: Move model_input, model_type from ModelEntry to ModelDeploymentCard (#3292) · 6ffd20a8
  Graham King authored Sep 30, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  6ffd20a8
- fix: fix backend in trtllm multinode example (#3311) · 50dfd3af
  Julien Mancuso authored Sep 30, 2025
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  50dfd3af
- fix: make HF cache mount point dynamic based on target (#3270) · 8c884345
  Keiven C authored Sep 30, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  8c884345
- test: create a helper function to send request directly to mocker instances (#3269) · 74a56676
  Paul Li authored Sep 29, 2025
```
Signed-off-by: Paul Li <zhixiong2008@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
```
  74a56676
- fix: operator planner metric port injection (#3294) · 16409eef
  Thomas Montfort authored Sep 29, 2025
  
  16409eef
- test: Allow prefill cancellation tests to fail (#3300) · 44a40a0b
  Jacky authored Sep 29, 2025
```
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
```
  44a40a0b
29 Sep, 2025 8 commits
- fix: more fixes for stable router benchmarking (#3264) · 3aa30778
  Yan Ru Pei authored Sep 29, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  3aa30778
- chore: Remove revision from ModelDeploymentCard (#3293) · 97a98546
  Graham King authored Sep 29, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  97a98546
- docs: remove hardcoded version in quick start (#3290) · e3df305b
  Anant Sharma authored Sep 29, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  e3df305b
- feat: use python3 in all examples (#3259) · a01b7992
  Julien Mancuso authored Sep 29, 2025
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  a01b7992
- ci: Limit cpus in docker processes (#3251) · 02209bbb
  Dillon Cullinan authored Sep 29, 2025
```
Signed-off-by: Dillon Cullinan <dcullinan@nvidia.com>
```
  02209bbb
- chore: add loopback as default address for network (#3250) · 1208f017
  akshaver authored Sep 29, 2025
  
  1208f017
- chore(build): Speedup rust github action job times and default cargo build time (#3220) · 65071f21
  Ryan McCormick authored Sep 29, 2025
```
Signed-off-by: Ryan McCormick <rmccormick@nvidia.com>
```
  65071f21
- fix: copy wheel from trtllm wheel stage (#3256) · f0709194
  Tushar Sharma authored Sep 29, 2025
```
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
```
  f0709194