Commits · b8e32933340835c8ee7eca6607ffbbefcf7e51a1 · OpenDAS / dynamo

23 Apr, 2026 2 commits
- test: skip test_sglang_indexers_sync in nightly only (DYN-2784) (#8539) · b8e32933
  Tushar Sharma authored Apr 22, 2026
```
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
```
  b8e32933
- chore(profiler): reshape replay_optimize into DGDR-aligned Pydantic specs (#8585) · 241b254d
  Yan Ru Pei authored Apr 22, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  241b254d
22 Apr, 2026 11 commits
- refactor: Removes obsolete TRT-LLM request-abort disable wiring and re-enables... · d401c1a4
  Jacky authored Apr 22, 2026
```
refactor: Removes obsolete TRT-LLM request-abort disable wiring and re-enables cancellation test coverage (#8562)
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
```
  d401c1a4
- fix(runtime): stop unconditional NATS connection with --discovery-backend file (#8398) · 6ba534a6
  Biswa Panda authored Apr 22, 2026
  
  6ba534a6
- test(fault_tolerance): replace hand-rolled SSE parser with openai SDK (#8536) · 48911230
  Dmitry Tokarev authored Apr 22, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
```
  48911230
- fix: remove the tool calling flaky test as the small model is not stable in... · 1aa5f219
  Richard Huo authored Apr 22, 2026
```
fix: remove the tool calling flaky test as the small model is not stable in generating Json format (#8523)
```
  1aa5f219
- feat: add TRTLLM text-to-image support (#8200) · 1b0334c8
  GuanLuo authored Apr 22, 2026
```
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
```
  1b0334c8
- test: Explicit None token thresholds disable Router initiated Rejection (#8477) · 9321c2e5
  Jacky authored Apr 22, 2026
```
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
```
  9321c2e5
- fix(responses): align wire shape with OpenResponses spec + add compliance CI (#8283) · 2a95ef63
  ishandhanani authored Apr 22, 2026
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>
```
  2a95ef63
- feat(vllm): multinode elastic EP support via Ray cluster + concurrent scale fix (#8216) · c4964f55
  Tzu-Ling Kan authored Apr 22, 2026
```
Signed-off-by: Tzu-Ling <tzulingk@nvidia.com>
```
  c4964f55
- fix(vllm): cap gpu_memory_utilization for encoder-only vision model load (#8466) · af32579e
  Qi Wang authored Apr 22, 2026
```
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
```
  af32579e
- refactor(tests): consolidate diffusion payload classes into shared payloads.py (#8435) · 9bf9709a
  Krishnan Prashanth authored Apr 22, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  9bf9709a
- fix(kvbm): Fix consolidator e2e tests (#8464) · d932d3b4
  Kris Hung authored Apr 22, 2026
  
  d932d3b4
21 Apr, 2026 11 commits

fix: Delete SQL tool call test for now since small models could occasionally... · 77a0051a

Richard Huo authored Apr 21, 2026

fix: Delete SQL tool call test for now since small models could occasionally generate malformed arguments with guided decoding (#8474)

77a0051a

test: stabilize nightly — skip engine-init failures, convert xfails to skips,... · cc583b2f

Dmitry Tokarev authored Apr 21, 2026

test: stabilize nightly — skip engine-init failures, convert xfails to skips, fix http URL validation regression (#8443)
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

cc583b2f

test: skip test_router_decisions_sglang_multiple_workers (DYN-2784) (#8441) · ddd19a68
Tushar Sharma authored Apr 21, 2026
```
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
```
ddd19a68
docs: document pipeline time budgets for lifecycle markers (#8374) · df888f68
Tushar Sharma authored Apr 21, 2026
```
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
```
df888f68
feat(tests): add --models-dir flag for read-only HF cache (#8362) · b6885977
Ran Rubin authored Apr 21, 2026
```
Signed-off-by: rrubin <rrubin@nvidia.com>
```
b6885977

fix: replace torch.load with safetensors and enable Rust frontend media... · f923777e

Indrajit Bhosale authored Apr 21, 2026

fix: replace torch.load with safetensors and enable Rust frontend media decoding for TRT-LLM multimodal (#8295)
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

f923777e

Format fix (#8440) · fd361c82
Dmitry Tokarev authored Apr 21, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
fd361c82

test(fault_tolerance): skip flaky sglang migration NATS combo, drop stale... · e6ce4db3

Dmitry Tokarev authored Apr 21, 2026

test(fault_tolerance): skip flaky sglang migration NATS combo, drop stale graceful_shutdown xfail (#8404)
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

e6ce4db3

test(serve): skip mm_agg_qwen2-audio-7b vLLM deployment on post-merge (#8411) · d795e1a4
Dmitry Tokarev authored Apr 21, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
```
d795e1a4
test(sglang): add pre_merge diffusion CI smoke tests for T2I and T2V (#8409) · 8679faa3
Krishnan Prashanth authored Apr 21, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
8679faa3
fix: Validate multimodal media URLs and load paths (#8282) · 8fba4f56
zhongdaor-nv authored Apr 20, 2026
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
```
8fba4f56

20 Apr, 2026 3 commits

fix: update the tool calling functionalities for sglang frontend processor to... · 8fd7de9a
Richard Huo authored Apr 20, 2026
```
fix: update the tool calling functionalities for sglang frontend processor to match with the latest sglang implementation (#8269)
```
8fd7de9a

fix: llava EPD deployment. add llava coverage (#8330) · e71f1d2b

GuanLuo authored Apr 20, 2026

Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>

e71f1d2b

feat: vLLM multinode elastic EP scaling support test (#8183) · f460f4e2
Tzu-Ling Kan authored Apr 20, 2026
```
Signed-off-by: Tzu-Ling <tzulingk@nvidia.com>
```
f460f4e2

17 Apr, 2026 2 commits
- feat(benchmarks): add sliding-window JSONL generation strategy (#8201) · 32ec044c
  Qi Wang authored Apr 17, 2026
```
Signed-off-by: furionw <qiwa@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  32ec044c
- fix(tests): keep shadows cold before failover quiesce (#8258) · c69e19e8
  Schwinn Saereesitthipitak authored Apr 17, 2026
```
Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
```
  c69e19e8
16 Apr, 2026 1 commit
- fix(replay): harden router scaling invariants (#8236) · a1e1954a
  Yan Ru Pei authored Apr 15, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  a1e1954a
15 Apr, 2026 4 commits
- fix(tests): compare shadow failover restore to RO footprint (#8247) · 6d4d0a61
  Schwinn Saereesitthipitak authored Apr 15, 2026
```
Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
Co-authored-by: Dan Gil <dagil@nvidia.com>
```
  6d4d0a61
- test(router): add single-worker mocker soak test (#8234) · 44cfbb68
  Yan Ru Pei authored Apr 15, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  44cfbb68
- feat: add TRT-LLM sleep/wake integration with GMS (#7575) · d96a2cf1
  hhzhang16 authored Apr 15, 2026
```
Co-authored-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  d96a2cf1
- ci: Move TRTLLM Fault Tolerance tests from post-merge back to nightly (#8210) · 71af9675
  Dmitry Tokarev authored Apr 15, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  71af9675
14 Apr, 2026 6 commits
- feat: add unified backend architecture with DynamoBackend (#8003) · da40db40
  Tanmay Verma authored Apr 14, 2026
```
Signed-off-by: Tanmay Verma <tanmayv@nvidia.com>
```
  da40db40
- feat: remove enable_nats usage (#7265) · af0ff07c
  Biswa Panda authored Apr 14, 2026
  
  af0ff07c
- feat(lora): add LoRA support for SGLang (#4769) · f9839161
  Biswa Panda authored Apr 14, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  f9839161
- feat: lmcache on CUDA 13 and ARM (#7534) · 21b44473
  Dmitry Tokarev authored Apr 14, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  21b44473
- fix: Reject local file inputs in ImageLoader (#8158) · 56f02422
  Graham King authored Apr 14, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  56f02422
- feat: add DGDR test suite (#7343) · 597b7249
  Ashna Mehrotra authored Apr 14, 2026
```
Signed-off-by: ashnamehrotra <ashnamehrotra@gmail.com>
```
  597b7249