All pull requests

Pull requests

• [Blog]: update Batch Gateway article and add benchmarking results

  Blog Post
  #544·lioraron opened Nov 10, 2026·

  ·
  2

• [Blog]: What Does Tracing Cost the EPP? Measuring OpenTelemetry Overhead in llm-d

  #543·albertoperdomo2 opened Nov 9, 2026·5 of 10 tasks·

  ·
  6

• [Blog]: AMD MoRI with llm-d: Long-Context GLM-5.3 on MI355X

  Blog Post
  #541·shikamd123 opened Nov 7, 2026·2 of 10 tasks·

  ·
  1

  1

• fix(ci): let the unstale workflow remove labels from PRs

  action
  #533·sugix opened Oct 29, 2026·

  ·
  1

• [Blog]: The Coordinator: Orchestrating Complex and Disaggregated Inference Without a Sidecar

  #532·roytman opened Oct 29, 2026Contributor·7 tasks done·

  ·
  9

• suffix-tree based speculative decode for rl blog post

  Blog Post
  #531·kfswain opened Oct 26, 2026·

  ·
  8

• [Blog]: Serving GLM-5.2 on SGLang with llm-d: Wide-EP, Host DRAM, and Shared Storage

  #530·tyuchn opened Oct 26, 2026·6 tasks done·

  ·
  25

  

• [blog] Add "Benchmarking Multi-Turn Multimodal Serving in llm-d" blog post

  Blog Post
  #528·cheng-hsiang-chiu opened Oct 23, 2026·9 of 10 tasks·

  ·
  9

• feat: Add Netlify PR previews for llm-d/llm-d documentation changes

  actionapproved
  #521·davidgs opened Oct 19, 2026Collaborator·7 of 10 tasks·

  ·
  13

• [blog] Add "Optimizing multi-cluster serving with black-box latency routing" blog post.

  #520·Mohammad-nassar10 opened Oct 19, 2026·10 tasks·

  ·
  1

• feat(i18n): enable zh-Hans documentation switching and freshness-aware sync

  lifecycle/stale
  #519·tangming1996 opened Oct 19, 2026Member·

  ·
  3

• [blog] Add "Multi-Cluster routing with llm-d" blog post.

  Blog Post
  #518·Mohammad-nassar10 opened Oct 18, 2026·10 tasks·

  ·
  14

• Redirect the merged async queue backend pages (llm-d/llm-d#2724)

  lifecycle/rotten
  #514·ahg-g opened Oct 9, 2026Collaborator·

  ·
  2

• Add blog guidelines and link from CONTRIBUTING

  #498·chcost opened Sep 28, 2026Contributor·

  ·
  5

• [Blog]: Multi-Tenant and Multi-Priority Model Serving with llm-d

  Blog Post
  #496·shimib opened Sep 22, 2026Member·2 of 10 tasks·

  ·
  23