Commits · c7bac97902c6893df6e016adaca66ee78d8f5b39 · OpenDAS / dynamo · GitLab

15 Mar, 2026 1 commit
- fix: patch vLLM 0.17.1 multi-node TP init ordering, enable gpu_2 pre-merge CI (#7357) · c7bac979
  Dmitry Tokarev authored Mar 14, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  c7bac979
14 Mar, 2026 14 commits
- docs: fix navbar Documentation link to point to Getting Started (#7385) · 0b665150
  dagil-nvidia authored Mar 14, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  0b665150
- chore: Enable lychee on PRs (#7383) · 48220950
  Dmitry Tokarev authored Mar 14, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  48220950
- docs(recipes): add experimental WIP note to Kimi-K2.5 recipe (#7381) · ed939f08
  Biswa Panda authored Mar 14, 2026
  
  ed939f08
- docs: fix broken links, typo, blog nav, and CUDA version (#7380) · 4ef8b8e6
  dagil-nvidia authored Mar 14, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  4ef8b8e6
- fix: remove cutlass-dsl stub that crashes TRT-LLM on CUDA 13.1 (#7372) · 5c48130d
  Tanmay Verma authored Mar 14, 2026
  
  5c48130d
- feat: standalone KV indexer runtime integration (#7295) · bba70a41
  Thomas Montfort authored Mar 14, 2026
  
  bba70a41
- chore(recipes): update container image tags to 1.0.0 (#7375) · 3718da8c
  Ben Hamm authored Mar 14, 2026
```
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  3718da8c
- feat(perf): add request-plane, transport, and work-handler metric definitions (#6735) · cec19d4d
  Biswa Panda authored Mar 14, 2026
  
  cec19d4d
- docs: add image-to-video support for vLLM-Omni in diffusion support matrix (#7374) · a3f805c7
  Ryan McCormick authored Mar 13, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  a3f805c7
- docs: revert #7371 (#7373) · 1da0ecd4
  dagil-nvidia authored Mar 13, 2026
  
  1da0ecd4
- feat: propagate OTEL trace context across E/P/D multimodal workers (#7239) · c263a99e
  jh-nv authored Mar 13, 2026
  
  c263a99e
- docs: use GitHub admonitions instead of Fern-native callouts (#7370) · 34f13a12
  dagil-nvidia authored Mar 13, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  34f13a12
- fix: prevent DYN_SYSTEM_PORT collisions in TRT-LLM EPD launch scripts (#7366) · da783ce0
  KrishnanPrash authored Mar 13, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  da783ce0
- docs: remove blog section from sidebar navigation (#7371) · 39310c5a
  dagil-nvidia authored Mar 13, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  39310c5a
13 Mar, 2026 25 commits
- docs: update KVBM diagram and bump container image tags to 1.0.0 (#7365) · 46dad85b
  dagil-nvidia authored Mar 13, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  46dad85b
- docs: use a different assets folder for each version (#7333) · 6b62df65
  Neal Vaidya authored Mar 13, 2026
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
```
  6b62df65
- fix: populate logprobs bytes and token fields in OpenAI-compatible responses (#6953) · 947939c7
  Biswa Panda authored Mar 13, 2026
  
  947939c7
- docs: remove duplicate title from introduction frontmatter (#7361) · 1d509252
  dagil-nvidia authored Mar 13, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  1d509252
- fix: reject multimodal requests when worker lacks --modality multimodal (#7065) · 4105de62
  KrishnanPrash authored Mar 13, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  4105de62
- ci: relax release branch version extraction to accept any release/* pattern (#7356) · b339c279
  Pavithra Vijayakrishnan authored Mar 13, 2026
```
Signed-off-by: pvijayakrish <pvijayakrish@nvidia.com>
Signed-off-by: Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  b339c279
- docs: rewrite architecture.md as a clearer system architecture narrative (#7022) · 5b415abb
  Anish authored Mar 13, 2026
```
Signed-off-by: athreesh <anish.maddipoti@utexas.edu>
Signed-off-by: Anish <80174047+athreesh@users.noreply.github.com>
Signed-off-by: akshatha-k <akshutk@gmail.com>
Co-authored-by: akshatha-k <33278067+akshatha-k@users.noreply.github.com>
Co-authored-by: akshatha-k <akshutk@gmail.com>
Co-authored-by: dagil-nvidia <dagil@nvidia.com>
```
  5b415abb
- ci: fit sglang multimodal EPD test on 1 GPU (#7046) · be2f1dc1
  KrishnanPrash authored Mar 13, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  be2f1dc1
- docs: add agentic inference post to blog landing page (#7359) · f744c7c3
  dagil-nvidia authored Mar 13, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  f744c7c3
- test: generalize router test infrastructure and expand documentations (#7327) · 33604afa
  Keiven C authored Mar 13, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  33604afa
- test(kv-router): use flush-and-settle helper in indexer tests (#7347) · cb9b1cd5
  Yan Ru Pei authored Mar 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  cb9b1cd5
- feat: harden ManagedProcess teardown, add xdist-safe tests (#6670) · 608405e0
  Keiven C authored Mar 13, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  608405e0
- feat(mocker): add --decode-speedup-ratio for speculative decoding simulation (#7349) · 7e07495f
  Yan Ru Pei authored Mar 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  7e07495f
- fix: Update custom-domain to support multiple domains (#7353) · 374107c0
  Fern Support authored Mar 13, 2026
```
Signed-off-by: Fern Support <126544928+fern-support@users.noreply.github.com>
```
  374107c0
- docs: modernize introduction page SVG figures (#7352) · 19c192cd
  dagil-nvidia authored Mar 13, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  19c192cd
- docs: update support matrix, release artifacts, and README for v1.0.0 (#7350) · 24fe435d
  dagil-nvidia authored Mar 13, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  24fe435d
- fix: Upgrade futures-util to 0.3.32 (#7346) · e6cb6847
  Graham King authored Mar 13, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  e6cb6847
- fix: inject tolerations for interpolation (profiling) (#7344) · 20f1c5a3
  hhzhang16 authored Mar 13, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  20f1c5a3
- feat: Add support for cpu builds in dockerfiles (#7139) · 23c42d83
  Sandeep Maddipatla authored Mar 13, 2026
```
Signed-off-by: Sandeep Maddipatla <sandeep.maddipatla@intel.com>
```
  23c42d83
- feat: Add NVTX markers for sglang EPD (#7079) · f29753dc
  Wang, Yi authored Mar 14, 2026
```
Signed-off-by: Wang, Yi <yi.a.wang@intel.com>
```
  f29753dc
- feat(kv-router): add Prometheus metrics to standalone indexer (#7339) · 5aa2f53f
  Yan Ru Pei authored Mar 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  5aa2f53f
- docs: add PR rebase guidelines and CI failure reproduction tips (#7298) · c8f7ce90
  Keiven C authored Mar 13, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  c8f7ce90
- chore: multi-arch frontend image (#7290) · 9f01dd25
  Ran Rubin authored Mar 13, 2026
  
  9f01dd25
- feat: GPU discovery extension using DCGM exporter for advanced metrics. (#6705) · 57648c19
  devivasudevan authored Mar 13, 2026
```
Signed-off-by: devivasudevan <49675305+devivasudevan@users.noreply.github.com>
```
  57648c19
- feat: enable intel XPU Dockerfile for Dev Target (#7134) · 1fc50263
  ZhengHongming888 authored Mar 13, 2026
```
Signed-off-by: Hongming Zheng <hongming.zheng@intel.com>
Co-authored-by: Zhan Xue <zhan.xue@intel.com>
```
  1fc50263