- 21 Apr, 2025 1 commit
-
-
Graham King authored
"echo_core" is an engine that echoes the post-processed request back to you so you can see the template. Good for testing. It needed an extra flag set to work correctly.
-
- 07 Apr, 2025 1 commit
-
-
Graham King authored
As a first step towards KV routing: - introduce a `--router-mode` in dynamo-run that only does random and round-robin right now. Not that interesting yet. - Make the vllm engine publish the KV events received from our patched vllm. Now we "just" need to connect the two. Easy right?
-
- 26 Mar, 2025 1 commit
-
-
Ryan Olson authored
-
- 14 Mar, 2025 1 commit
-
-
Ryan McCormick authored
-
- 08 Mar, 2025 1 commit
-
-
Neelay Shah authored
Co-authored-by:Biswa Panda <biswa.panda@gmail.com>
-
- 07 Mar, 2025 1 commit
-
-
Graham King authored
There are two etcd keys: - The service - The model The second one is the interesting one for us. Previously we confused the two.
-
- 05 Mar, 2025 1 commit
-
-
Neelay Shah authored
Co-authored-by:Graham King <grahamk@nvidia.com>
-
- 28 Feb, 2025 1 commit
-
-
Paul Hendricks authored
-
- 27 Feb, 2025 3 commits
-
-
Paul Hendricks authored
-
Paul Hendricks authored
-
Paul Hendricks authored
-
- 26 Feb, 2025 1 commit
-
-
Paul Hendricks authored
Co-authored-by:Graham King <grahamk@nvidia.com>
-
- 25 Feb, 2025 2 commits
-
-
Alec authored
Co-authored-by:aflowers <aflowers@nvidia.com>
-
Neelay Shah authored
Signed-off-by:
Neelay Shah <neelays@nvidia.com> Co-authored-by:
Ryan McCormick <rmccormick@nvidia.com>
-