- 31 May, 2025 3 commits
-
-
Ryan McCormick authored
-
Hongkuan Zhou authored
-
mohammedabdulwahhab authored
-
- 30 May, 2025 5 commits
-
-
Biswa Panda authored
-
Kris Hung authored
-
Alec authored
-
Biswa Panda authored
-
Tanmay Verma authored
-
- 29 May, 2025 2 commits
-
-
J Wyman authored
This change corrects the README.md file in the examples/multimodal folder: - Correct "vllm worker" to "decode worker" - Correct assertion that data is moved via NATS when embeddings are moved via RDMA. Additionally, this change updates the textual graphs with Mermaid graphs for improved presentation on github.com.
-
Hongkuan Zhou authored
Signed-off-by:
Hongkuan Zhou <tedzhouhk@gmail.com> Co-authored-by:
coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
-
- 28 May, 2025 4 commits
-
-
Kris Hung authored
Co-authored-by:J Wyman <jwyman@nvidia.com>
-
Kris Hung authored
-
Neelay Shah authored
-
ishandhanani authored
-
- 27 May, 2025 6 commits
-
-
ishandhanani authored
Signed-off-by:
ishandhanani <82981111+ishandhanani@users.noreply.github.com> Co-authored-by:
Neelay Shah <neelays@nvidia.com>
-
mohammedabdulwahhab authored
Co-authored-by:Anna Tchernych <atchernych@nvidia.com>
-
kYLe authored
-
Shuaiyi Zhang authored
Signed-off-by:
Shuaiyi Zhang <zhangsy28@lenovo.com> Co-authored-by:
Shuaiyi Zhang <zhangsy28@lenovo.com> Co-authored-by:
Yan Ru Pei <yanrpei@gmail.com>
-
Akash authored
Signed-off-by:Akash <akpaul@nvidia.com>
-
J Wyman authored
-
- 23 May, 2025 1 commit
-
-
Hongkuan Zhou authored
-
- 22 May, 2025 2 commits
-
-
Hongkuan Zhou authored
Co-authored-by:root <root@kkranen-dt.nvidia.com>
-
Hongkuan Zhou authored
-
- 21 May, 2025 3 commits
-
-
Suman Tatiraju authored
Signed-off-by:
Suman Tatiraju <167138127+statiraju@users.noreply.github.com> Signed-off-by:
Anant Sharma <anants@nvidia.com> Co-authored-by:
Anant Sharma <anants@nvidia.com> Co-authored-by:
Dmitry Tokarev <dtokarev@nvidia.com> Co-authored-by:
ishandhanani <82981111+ishandhanani@users.noreply.github.com> Co-authored-by:
Kristen Kelleher <kkelleher@nvidia.com> Co-authored-by:
Suman Tatiraju <statiraju@statiraju-mlt.client.nvidia.com> Co-authored-by:
Hannah Zhang <hannahz@nvidia.com>
-
Biswa Panda authored
-
Tanmay Verma authored
-
- 20 May, 2025 3 commits
-
-
julienmancuso authored
-
Tanmay Verma authored
-
Hongkuan Zhou authored
-
- 19 May, 2025 2 commits
-
-
Graham King authored
We can now do this: - Node 1: ``` dynamo-run in=http out=dyn ``` - Node 2 and 3, two instances of component 'backend' in the nemotron_ultra pipeline: ``` dynamo-run in=dyn://nemotron_ultra.backend.generate out=vllm /data/models/NemotronUltra ``` - Node 4 and 5, two instances of the 'backend' component in nemotron_super pipeline: ``` dynamo-run in=dyn://nemotron_super.backend.generate out=vllm /data/models/NemotronSuper ``` The ingress node will discover all four instances and route correctly. We have been planning for this for a long time now. As part of this auto-discovery is now always `out=dyn`, with no extra URL parts. Previously it could only route to a single pipeline. Also: - Refactor endpoint / instance naming now that I understand them - Fix removing models when their instance stops.
-
ishandhanani authored
-
- 16 May, 2025 3 commits
-
-
ptarasiewiczNV authored
-
Ryan McCormick authored
-
Biswa Panda authored
-
- 15 May, 2025 3 commits
-
-
mohammedabdulwahhab authored
-
Biswa Panda authored
-
Ryan McCormick authored
-
- 14 May, 2025 1 commit
-
-
ishandhanani authored
Co-authored-by:ishandhanani <ishandhananai@gmail.com>
-
- 12 May, 2025 2 commits
-
-
Hongkuan Zhou authored
-
Hongkuan Zhou authored
Co-authored-by:Biswa Panda <biswa.panda@gmail.com>
-