- 16 Sep, 2025 1 commit
-
-
Graham King authored
Signed-off-by:Graham King <grahamk@nvidia.com>
-
- 22 Aug, 2025 1 commit
-
-
Graham King authored
-
- 19 Aug, 2025 1 commit
-
-
Yan Ru Pei authored
-
- 14 Aug, 2025 1 commit
-
-
Jorge António authored
Co-authored-by:Yan Ru Pei <yanrpei@gmail.com>
-
- 07 Aug, 2025 1 commit
-
-
Yan Ru Pei authored
-
- 08 Jul, 2025 1 commit
-
-
Yan Ru Pei authored
Signed-off-by:
Yan Ru Pei <yanrpei@gmail.com> Co-authored-by:
Alec <35311602+alec-flowers@users.noreply.github.com>
-
- 15 May, 2025 1 commit
-
-
Graham King authored
The Python bindings use the default value for RouterMode. Previously that was Random (good), but now it became None (bad). Remove the option and clean up the duplicate RouterMode. I was trying to avoid putting the `KV` enum in dynamo-runtime. Turns out adding those two characters gives us a healthy simplification, and restores the old default router value. Also clean up two noisy log messages when waiting for KV routing metrics to start in worker.
-
- 14 May, 2025 1 commit
-
-
Graham King authored
Router: ``` dynamo-run in=http out=dyn://dynamo.endpoint.generate --router-mode kv ``` Worker (* N): ``` dynamo-run in=dyn://dynamo.endpoint.generate out=vllm /data/llms/Qwen/Qwen3-4B ``` You need patched vllm and the C bindings `.so`. Full docs in the updated guide: `docs/guides/dynamo_run.md`. This gives us a pure-Rust ingress node: OpenAI compliant HTTP server + Pre-processor + KV-aware router.
-
- 02 Apr, 2025 1 commit
-
-
Ryan Olson authored
-
- 17 Mar, 2025 1 commit
-
-
GuanLuo authored
-
- 11 Mar, 2025 1 commit
-
-
Alec authored
-
- 08 Mar, 2025 1 commit
-
-
Neelay Shah authored
Co-authored-by:Biswa Panda <biswa.panda@gmail.com>
-
- 06 Mar, 2025 1 commit
-
-
GuanLuo authored
-