Commits · 52090e2e769ff1b9a4b07fcd7ca79e58a70dfc90 · OpenDAS / dynamo

"lib/llm/vscode:/vscode.git/clone" did not exist on "e55ebec56224424a906cfb0028620c7e0709351d"

29 Oct, 2025 2 commits
- feat: refactor vllm multimodal example (#3634) · 52090e2e
  Ayush Agarwal authored Oct 29, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  52090e2e
- feat: add prefill worker metrics support for vLLM (#3949) · 4bce7f75
  Keiven C authored Oct 29, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  4bce7f75
28 Oct, 2025 2 commits
- feat: mocker disagg (#3833) · cc4c3516
  Yan Ru Pei authored Oct 28, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  cc4c3516
- chore(runtime): Do not expose etcd lease ID (#3915) · c78b5901
  Graham King authored Oct 28, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  c78b5901
27 Oct, 2025 2 commits

feat: turn profiling k8s jobs into sample DGDR requests (#3864) · 6a84ffd3

hhzhang16 authored Oct 27, 2025


Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: Hongkuan Zhou <tedzhouhk@gmail.com>

6a84ffd3

refactor: remove hardcoded /workspace paths across tests (#3888) · 07cf0744
Keiven C authored Oct 27, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
07cf0744

24 Oct, 2025 3 commits
- fix: ignore stop key in vllm sampling params (#3879) · a79151c8
  ryan-lempka authored Oct 24, 2025
```
Signed-off-by: Ryan Lempka <rlempka@nvidia.com>
```
  a79151c8
- fix: Fix sglang multimodal test (#3862) · 77cecf4e
  Kris Hung authored Oct 24, 2025
```
Signed-off-by: krishung5 <krish@nvidia.com>
```
  77cecf4e
- feat: TensorRT-LLM and SGLang metrics validation (part 2/3 + 3/3) (#3842) · 3e015595
  Keiven C authored Oct 23, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  3e015595
23 Oct, 2025 2 commits
- chore: restructure mocker cli args handling, to include prefill/decode (#3847) · 41ff394f
  Yan Ru Pei authored Oct 23, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  41ff394f
- perf: cache compiled regex patterns in prometheus metrics filtering (#3825) · 7bb6368f
  Keiven C authored Oct 22, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  7bb6368f
22 Oct, 2025 4 commits

docs: address Harry/VDR feedback + fixing broken links across repository (#3802) · c6b59045

Anish authored Oct 22, 2025


Signed-off-by: Harry Kim <harry_kim@live.com>
Signed-off-by: athreesh <anish.maddipoti@utexas.edu>
Signed-off-by: akshatha-k <33278067+akshatha-k@users.noreply.github.com>
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
Co-authored-by: Harry Kim <harry_kim@live.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: akshatha-k <33278067+akshatha-k@users.noreply.github.com>
Co-authored-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>

c6b59045

fix: bug fixes for planner tests (#3821) · 7b2f95e4
hhzhang16 authored Oct 22, 2025
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
7b2f95e4
chore: no need to publish kv events for decode vllm worker (#3819) · fb294b90
Yan Ru Pei authored Oct 22, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
fb294b90
feat: add TensorRT-LLM Prometheus metrics support with prefixing + filtering (#3676) · f93b619a
Keiven C authored Oct 22, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
f93b619a

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
17 Oct, 2025 1 commit
- fix: standardize all planner ttft/itl units to float ms and fix docs (#3673) · ee56782b
  William Arnold authored Oct 17, 2025
```
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
```
  ee56782b
16 Oct, 2025 2 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
- feat: dp rank routing (#3597) · f978f4d1
  Yan Ru Pei authored Oct 15, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  f978f4d1
15 Oct, 2025 1 commit
- feat: Python binding to download a model. (#3593) · ab0da582
  Graham King authored Oct 15, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  ab0da582
14 Oct, 2025 4 commits
- chore: update sglang to 0.5.3.post1 to take advantage of container + doc cleanup (#3621) · c6e3db5e
  ishandhanani authored Oct 14, 2025
  
  c6e3db5e
- fix: Add support for single element arrays for chat and completions prompts (#3482) · 3dc25129
  zhongdaor-nv authored Oct 14, 2025
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
```
  3dc25129
- feat: catch Trtllm engine exceptions (#3544) · 1ad2a3b8
  Tzu-Ling Kan authored Oct 14, 2025
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  1ad2a3b8
- fix: only log config on `debug` log level, fix trtllm warnings (#3590) · 7b0fad3f
  William Arnold authored Oct 14, 2025
```
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
```
  7b0fad3f
11 Oct, 2025 2 commits
- feat: implement custom backend metrics for NIM (#3266) · 65cc5337
  Keiven C authored Oct 10, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  65cc5337
- 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 4 commits
- feat: Sglang Request cancellation (#3465) · 2d0dab74
  Indrajit Bhosale authored Oct 10, 2025
```
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
```
  2d0dab74
- ci: TRTLLM & SGLang Unit Tests (for --custom-jinja-template) (#3472) · a3d46840
  KrishnanPrash authored Oct 10, 2025
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  a3d46840
- feat: add Rust-to-Python const code generator for prometheus_names.py (#3425) · f2ba58e5
  Keiven C authored Oct 10, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  f2ba58e5
- fix: Send last token batch when finish_reason is set (#3531) · 111c6814
  Ryan McCormick authored Oct 09, 2025
  
  111c6814
09 Oct, 2025 3 commits
- feat: sglang prefill router + bump to `0.5.3` (#3498) · 51f65757
  ishandhanani authored Oct 09, 2025
  
  51f65757
- refactor: remove vllm prefill worker background loop check (#3529) · 07a64744
  Yan Ru Pei authored Oct 09, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  07a64744
- chore: Remove clear_namespace script (#3519) · e9a71009
  Graham King authored Oct 09, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  e9a71009
08 Oct, 2025 7 commits
- fix: remove _version import in config_dump (#3502) · 9b5bab72
  William Arnold authored Oct 08, 2025
```
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
```
  9b5bab72
- 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
- chore: Remove llama.cpp engine (#3499) · 0aa0768f
  Graham King authored Oct 08, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  0aa0768f
- fix: update dynamo namespace env var usage (#3477) · 552146f2
  Biswa Panda authored Oct 08, 2025
  
  552146f2
- feat: prefill routing for trtllm (#3471) · f3987f6c
  Yan Ru Pei authored Oct 08, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  f3987f6c
- fix: frontend component handles graceful shutdown (#3481) · 2d59861e
  Thomas Montfort authored Oct 08, 2025
  
  2d59861e
- chore: Remove GGUF support (#3488) · 1b1265e6
  Graham King authored Oct 08, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  1b1265e6