Commits · d712ce8d0df3b74e020153016c509f249c679d20 · OpenDAS / dynamo

"benchmarks/vscode:/vscode.git/clone" did not exist on "b482b9a5b13ba7d126adabbedb3ba66f48d4d83b"

22 Oct, 2025 1 commit
- fix: disagg dp attention needs host 0.0.0.0 (#3809) · 79ad7f36
  ishandhanani authored Oct 22, 2025
  
  79ad7f36
21 Oct, 2025 1 commit
- feat: bake prefill router into frontend, supporting vllm for now (#3762) · e01c6e99
  Yan Ru Pei authored Oct 21, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  e01c6e99
16 Oct, 2025 3 commits
- docs: reorganizing documentation to make things clearer (#3658) · 598cbbb7
  Anish authored Oct 16, 2025
```
Signed-off-by: athreesh <anish.maddipoti@utexas.edu>
Co-authored-by: Claude <noreply@anthropic.com>
```
  598cbbb7
- docs: move SGLang and vLLM Prometheus metrics documentation to docs path (#3677) · f4cd71f3
  Keiven C authored Oct 16, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  f4cd71f3
- fix: add `--host` to k8s and bump sgl version (#3666) · 9a002b30
  ishandhanani authored Oct 15, 2025
  
  9a002b30
15 Oct, 2025 2 commits
- fix: Reduce memory usage to avoid vLLM dsr1 OOM (#3660) · 29f5b822
  Kris Hung authored Oct 15, 2025
  
  29f5b822
- feat: Replace genai-perf with aiperf in components/backends (#3528) · a7badb85
  Harshini Komali authored Oct 15, 2025
```
Signed-off-by: lkomali <lkomali@nvidia.com>
```
  a7badb85
14 Oct, 2025 1 commit
- chore: typo and new commands (#3617) · 4c4130e3
  ishandhanani authored Oct 14, 2025
  
  4c4130e3
11 Oct, 2025 1 commit

feat: add SGLang and vLLM passthrough metrics on Dynamo backend worker (#3539) · 55e458d8

Keiven C authored Oct 10, 2025


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

55e458d8

10 Oct, 2025 1 commit

docs: move all md files from components to docs (#3440) · 0a2a820b

Anant Sharma authored Oct 09, 2025


Signed-off-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: Anish <80174047+athreesh@users.noreply.github.com>

0a2a820b

09 Oct, 2025 6 commits
- refactor: remove sglang config and util files from components (#3467) · 03bdced9
  Anant Sharma authored Oct 09, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  03bdced9
- feat: sglang prefill router + bump to `0.5.3` (#3498) · 51f65757
  ishandhanani authored Oct 09, 2025
  
  51f65757
- docs: add vLLM KVBM 2P2D example due to a special ENV VAR to note (#3526) · 44012a24
  Ziqi Fan authored Oct 09, 2025
```
Signed-off-by: Ziqi Fan <ziqif@nvidia.com>
```
  44012a24
- chore: add sample KVBM related k8s deployment manifests (#3523) · 5f7c1f7e
  Ziqi Fan authored Oct 09, 2025
```
Signed-off-by: Ziqi Fan <ziqif@nvidia.com>
```
  5f7c1f7e
- chore: Remove clear_namespace script (#3519) · e9a71009
  Graham King authored Oct 09, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  e9a71009
- fix: fix config updates on deep copy not propagating back (#3512) · bd28e442
  Hongkuan Zhou authored Oct 08, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  bd28e442
08 Oct, 2025 2 commits
- feat: enable KVBM to support PD disagg in Dynamo vLLM (#3352) · 9975cb9f
  Ziqi Fan authored Oct 08, 2025
```
Signed-off-by: Ziqi Fan <ziqif@nvidia.com>
```
  9975cb9f
- fix: update dynamo namespace env var usage (#3477) · 552146f2
  Biswa Panda authored Oct 08, 2025
  
  552146f2
07 Oct, 2025 5 commits
- feat: pre-deployment profiling automatically generates and deploys optimized... · 83e259a7
  Hongkuan Zhou authored Oct 07, 2025
```
feat: pre-deployment profiling automatically generates and deploys optimized DGD with planner (#3441)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  83e259a7
- chore: update guide for reasoning & tool calling parser with gpt-oss on trtllm (#3262) · 55f7e637
  zhongdaor-nv authored Oct 07, 2025
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
```
  55f7e637
- docs: Update trtllm multinode multimodal docs (#3369) · 04aafa9a
  Indrajit Bhosale authored Oct 07, 2025
```
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
```
  04aafa9a
- chore: Clean up for sglang multimodal example (#3420) · ddbb4f50
  Kris Hung authored Oct 06, 2025
```
Signed-off-by: krishung5 <krish@nvidia.com>
```
  ddbb4f50
- feat: Add embedding support to sgl backend (#3427) · d809906e
  Kris Hung authored Oct 06, 2025
```
Signed-off-by: krishung5 <krish@nvidia.com>
```
  d809906e
06 Oct, 2025 1 commit
- refactor: clean up sglang apis [1/n] (#3432) · de5c39df
  ishandhanani authored Oct 06, 2025
  
  de5c39df
03 Oct, 2025 2 commits

fix: remove VSWA user prompts, since we need a lot more updates to get it working (#3404) · c48f49a4
Richard Huo authored Oct 03, 2025
```
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
```
c48f49a4

docs: add Planner Quickstart doc (#3358) · 89cf9107

hhzhang16 authored Oct 03, 2025


Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Signed-off-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>
Co-authored-by: Hongkuan Zhou <tedzhouhk@gmail.com>

89cf9107

02 Oct, 2025 3 commits
- fix: correctly parse subcomponent in sla-planner + deploy/doc update (#3363) · cfe74445
  Hongkuan Zhou authored Oct 02, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  cfe74445
- fix: add a note for users to use VSWA feature after 0.5.1 release (#3380) · 92b8fe07
  Richard Huo authored Oct 02, 2025
```
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
```
  92b8fe07
- feat: Add multimodal EPD for Sglang (#3230) · 62661cce
  Kris Hung authored Oct 01, 2025
```
Signed-off-by: krishung5 <krish@nvidia.com>
```
  62661cce
01 Oct, 2025 4 commits
- feat: restructure source code for python packaging (#3201) · 836d7417
  Anant Sharma authored Oct 01, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  836d7417
- 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: 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
30 Sep, 2025 7 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: 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
- fix: Install right versions of the dependencies for tensorrtllm (#3218) · c265cd67
  Tanmay Verma authored Sep 30, 2025
  
  c265cd67
- 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
- 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