Commits · 7731b0245cf53eb81440d9dfeeb8c2dd91065f42 · OpenDAS / dynamo

23 Oct, 2025 1 commit
- chore: Use KeyValueStoreManager instead of etcd::Client (#3822) · 7731b024
  Graham King authored Oct 23, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  7731b024
22 Oct, 2025 1 commit

fix: enhance gRPC frontend to return output in raw content field for Triton... · d68e4b8a

GuanLuo authored Oct 22, 2025

fix: enhance gRPC frontend to return output in raw content field for Triton client compatibility (#3600)
Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>

d68e4b8a

21 Oct, 2025 1 commit
- chore: tool calling -- sglang e2e tests (#3650) · 43329cd6
  Elyas Mehtabuddin authored Oct 20, 2025
  
  43329cd6
17 Oct, 2025 1 commit
- refactor: Make `nats_client` optional internally (#3705) · 66fd6f84
  Graham King authored Oct 17, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  66fd6f84
16 Oct, 2025 2 commits
- fix: deepseek tool parsing fixed (#3557) · e41fa1a0
  Elyas Mehtabuddin authored Oct 16, 2025
  
  e41fa1a0
- feat: dp rank routing (#3597) · f978f4d1
  Yan Ru Pei authored Oct 15, 2025
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  f978f4d1
14 Oct, 2025 1 commit
- test: Break parsers -> llm dependency (#3607) · 972adc37
  Graham King authored Oct 14, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  972adc37
13 Oct, 2025 1 commit
- feat: Metric histogram buckets configureable from env (#3562) · f0065bb4
  William Arnold authored Oct 13, 2025
```
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
```
  f0065bb4
10 Oct, 2025 1 commit
- chore: remove deprecated nvext parameters for 6.0 (#3551) · b954a249
  ryan-lempka authored Oct 10, 2025
  
  b954a249
08 Oct, 2025 1 commit
- chore: Remove GGUF support (#3488) · 1b1265e6
  Graham King authored Oct 08, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  1b1265e6
07 Oct, 2025 1 commit
- chore(discovery): Watch/publish ModelDeploymentCard instead of ModelEntry (#3350) · 81162dfe
  Graham King authored Oct 07, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  81162dfe
06 Oct, 2025 1 commit
- chore: added vllm tool + reasoning data (#3416) · d4b09631
  Ayush Agarwal authored Oct 06, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  d4b09631
03 Oct, 2025 1 commit
- fix: namespace not being considered on model delete (#3403) · c7cdc8cd
  Chi McIsaac authored Oct 03, 2025
```
Signed-off-by: Chi McIsaac <chixie.mcisaac@gmail.com>
```
  c7cdc8cd
01 Oct, 2025 2 commits
- feat: reasoning parser transformation (#3295) · 2a2bf58a
  Ayush Agarwal authored Oct 01, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  2a2bf58a
- 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
30 Sep, 2025 2 commits
- fix: Edge cases for Parallel tool calling (#3283) · 9088e1b5
  Elyas Mehtabuddin authored Sep 30, 2025
```
Signed-off-by: Elyas Mehtabuddin <emehtabuddin@nvidia.com>
```
  9088e1b5
- 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
29 Sep, 2025 2 commits
- chore: relaxing constraints on metadata field, adding metadata field to completions API (#3240) · 13156361
  nv-nedelman-1 authored Sep 29, 2025
```
Signed-off-by: Nicholas Edelman <nedelman@nvidia.com>
```
  13156361
- feat: enable parallel tool calling and add testing (#3188) · 67e1f6ee
  Elyas Mehtabuddin authored Sep 29, 2025
```
Signed-off-by: Elyas Mehtabuddin <emehtabuddin@nvidia.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  67e1f6ee
26 Sep, 2025 1 commit
- feat: replace polling with event-driven metrics updates (#3207) · 53f3d2af
  Keiven C authored Sep 26, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  53f3d2af
24 Sep, 2025 2 commits

feat: add NIM FE (num_request_max) + runtime config metrics with periodic polling (#3107) · 116b9b43
Keiven C authored Sep 24, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
116b9b43

feat: tensor type for generic inference. (#2746) · 6ba64c31

GuanLuo authored Sep 24, 2025


Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
Co-authored-by: Olga Andreeva <124622579+oandreeva-nv@users.noreply.github.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

6ba64c31

23 Sep, 2025 2 commits
- feat: JailedStream (#3034) · c63cceaa
  Ryan Olson authored Sep 23, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  c63cceaa
- chore: added middleware layer to catch json validation errors (#3182) · 4c56c8ae
  Ayush Agarwal authored Sep 23, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  4c56c8ae
18 Sep, 2025 1 commit
- chore: set default tool calling behaviour to be disabled (#3096) · 37322011
  Ayush Agarwal authored Sep 17, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  37322011
17 Sep, 2025 3 commits
- fix: harmony parser streaming fix (#3074) · cd814377
  Ayush Agarwal authored Sep 17, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
Signed-off-by: Graham King <grahamk@nvidia.com>
Co-authored-by: Graham King <grahamk@nvidia.com>
```
  cd814377
- feat: add chat_template_kwargs param to v1/chat/completion (#3016) · eb6722e3
  Chi McIsaac authored Sep 17, 2025
```
Signed-off-by: Chi McIsaac <chixie.mcisaac@gmail.com>
```
  eb6722e3
- feat: Make part of discovery re-usable (#3073) · 9060ce12
  Graham King authored Sep 17, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  9060ce12
16 Sep, 2025 2 commits
- chore(llm): Remove extra license headers (#3065) · bc0a7633
  Graham King authored Sep 16, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  bc0a7633
- fix: implement OpenAI-compliant usage stats for streaming responses (#3022) · aa80ac41
  Ryan Olson authored Sep 16, 2025
```
Signed-off-by: Ryan Olson <rolson@nvidia.com>
```
  aa80ac41
15 Sep, 2025 2 commits

fix: Handle invalid JSON in config.json (#3043) · b1186aee
Graham King authored Sep 15, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
b1186aee

feat: Tool calling support stream=True (#2932) · 2a61e29e

Elyas Mehtabuddin authored Sep 15, 2025


Signed-off-by: ayushag <ayushag@nvidia.com>
Signed-off-by: Biswa Panda <biswa.panda@gmail.com>
Co-authored-by: ayushag <ayushag@nvidia.com>
Co-authored-by: Biswa Panda <biswa.panda@gmail.com>

2a61e29e

05 Sep, 2025 1 commit
- fix: Load the tokenizer JSON once for chat and completions. (#2910) · cb5a657a
  Graham King authored Sep 05, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  cb5a657a
04 Sep, 2025 1 commit
- chore: frontend API changes for thinking budget (#2848) · 8d30753f
  Bhuvan Agrawal authored Sep 03, 2025
```
Signed-off-by: Bhuvan Agrawal <11240550+bhuvan002@users.noreply.github.com>
```
  8d30753f
03 Sep, 2025 3 commits

refactor: Split ModelType to ModelInput for request and response type;... · 27fad26f

Olga Andreeva authored Sep 03, 2025

refactor: Split ModelType to ModelInput for request and response type; ModelType for the supported workloads (#2714)
Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
Co-authored-by: Guan Luo <gluo@nvidia.com>
Co-authored-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>

27fad26f

feat: Add --custom-jinja-template argument to pass a custom chat template for vLLM (#2829) · c920cbd9
KrishnanPrash authored Sep 03, 2025
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
c920cbd9
feat: dynamo namespace isolation (#2394) · c6becbc8
Biswa Panda authored Sep 03, 2025
```
Signed-off-by: Biswa Panda <biswa.panda@gmail.com>
```
c6becbc8

29 Aug, 2025 2 commits
- chore: added include_stop_str_in_output (#2782) · 1f6b83be
  Ayush Agarwal authored Aug 29, 2025
  
  1f6b83be
- chore: deprecate nvext.top_k and nvext.repetition_penalty and make available top level (#2767) · 63f5bbc0
  ryan-lempka authored Aug 28, 2025
```
Signed-off-by: Ryan Lempka <rlempka@nvidia.com>
```
  63f5bbc0
28 Aug, 2025 1 commit
- feat: Prevent double-tokenization when EPP picks worker (#2559) · 7d13b6e3
  atchernych authored Aug 28, 2025
  
  7d13b6e3