Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: ai-dynamo/dynamo
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: a7cbbe789aeb64a850437e2e194d7818a504f357
Choose a base ref
...
head repository: ai-dynamo/dynamo
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: 44f78896dd2e3e0cb3c496dc574a14e142fcc512
Choose a head ref
  • 8 commits
  • 46 files changed
  • 8 contributors

Commits on Aug 7, 2025

  1. feat: LMCache integration in newest ux (#2079) 

    Signed-off-by: ZichengMa <zichengma1225@gmail.com>
Co-authored-by: Ziqi Fan <ziqif@nvidia.com>
    @ZichengMa @ziqifan617
    ZichengMa and ziqifan617 authored Aug 7, 2025
    Configuration menu
    Copy the full SHA
    784da90 View commit details
    Browse the repository at this point in the history

  2. fix: Reduce disk space usage in pre-merge-rust action (removes unnece… 

    …ssary sccache artifacts) (#2337)
    @rmccorm4
    rmccorm4 authored Aug 7, 2025
    Configuration menu
    Copy the full SHA
    5fad47f View commit details
    Browse the repository at this point in the history

  3. feat: DIS-323 [trtllm backend publisher] only publish kv event with t… 

    …he biggest window size to support kv routing with variable sliding window attention (#2241)
    @richardhuo-nv
    richardhuo-nv authored Aug 7, 2025
    Configuration menu
    Copy the full SHA
    2cf6776 View commit details
    Browse the repository at this point in the history

  4. refactor: Rename HTTP server to metrics server in worker process (#2318)

    @yinggeh
    yinggeh authored Aug 7, 2025
    Configuration menu
    Copy the full SHA
    254f481 View commit details
    Browse the repository at this point in the history

  5. fix: improve HF token handling in preprocessor tests (#2321) 

    Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
    @keivenchang
    keivenchang and keivenchang authored Aug 7, 2025
    Configuration menu
    Copy the full SHA
    ccc8815 View commit details
    Browse the repository at this point in the history

  6. chore: Remove service_name from ModelDeploymentCard 

    We had two names in the ModelDeploymentCard: display_name and
service_name. They were either always identical, or service_name was a
[slug](https://sentry.io/answers/slug-in-django/)-ified version of the
display_name.

Having two names is confusing, especially for #2267 .

Now we only have `display_name`. The HTTP server gets to decide how to
translate that to the `model` HTTP field (if at all), it's not in the
card. In practice it still uses a slug.

Most of the code change in here is because I merged
`model_card/create.rs` and `model_card/model.rs`. It always confused me
why the object and it's implementation should be in separate files
(modules). It confused Rust too, we had to make fields `pub` just to access them.
I suspect it was a pattern from a different language mis-applied to Rust. Is fixed.
    @grahamking
    grahamking committed Aug 7, 2025
    Configuration menu
    Copy the full SHA
    80f8c61 View commit details
    Browse the repository at this point in the history

  7. fix: clippy

    @grahamking
    grahamking committed Aug 7, 2025
    Configuration menu
    Copy the full SHA
    9b7666f View commit details
    Browse the repository at this point in the history

  8. perf: Improve capitalize from N allocs to 3. 

    Thank you Code Rabbit for noticing, and Gemini Pro 2.5 for the detailed
perf comparison. What a beautiful future.
    @grahamking
    grahamking committed Aug 7, 2025
    Configuration menu
    Copy the full SHA
    44f7889 View commit details
    Browse the repository at this point in the history
Loading