Skip to content

Releases: neuralmagic/vllm-vcr

Release list

nightly (vLLM main @ b80ce9dd2f30)

nightly (vLLM main @ b80ce9dd2f30) Pre-release
Pre-release

Choose a tag to compare

View all tags
@github-actions github-actions released this 21 Jun 07:39
nightly
f701bbd
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Rolling build against vLLM main commit b80ce9dd2f30913b3b054308a09bd2d86ec6202f, overwritten each night. Not a stable release; tracks upstream HEAD to surface protocol drift early.

Loading

v0.1.3

v0.1.3 Latest
Latest

Choose a tag to compare

View all tags
@github-actions github-actions released this 19 Jun 18:19
v0.1.3
47c69dc
This commit was signed with the committer’s verified signature.
wseaton Will Eaton
GPG key ID: BB7D10BBFF3BFB61
Verified
Learn about vigilant mode.

What's Changed

  • support s3:// URIs for trace capture, replay, and inspection (#8) by @wseaton in #15

Full Changelog: v0.1.2...v0.1.3

Contributors

wseaton
Assets 32

v0.1.2

v0.1.2

Choose a tag to compare

View all tags
@github-actions github-actions released this 18 Jun 22:13
v0.1.2
d6e00d8
This commit was signed with the committer’s verified signature.
wseaton Will Eaton
GPG key ID: BB7D10BBFF3BFB61
Verified
Learn about vigilant mode.

Full Changelog: v0.1.1...v0.1.2

Loading

v0.1.1

v0.1.1

Choose a tag to compare

View all tags
@github-actions github-actions released this 18 Jun 15:31
v0.1.1
dc147a4
This commit was signed with the committer’s verified signature.
wseaton Will Eaton
GPG key ID: BB7D10BBFF3BFB61
Verified
Learn about vigilant mode.

Full Changelog: v0.1.0...v0.1.1

Loading

v0.1.0

v0.1.0

Choose a tag to compare

View all tags
@github-actions github-actions released this 17 Jun 20:21
v0.1.0
4eef922
This commit was signed with the committer’s verified signature.
wseaton Will Eaton
GPG key ID: BB7D10BBFF3BFB61
Verified
Learn about vigilant mode.

What's Changed

  • Kv cache events and ci by @wseaton in #1
  • Lora simulation by @wseaton in #2
  • refactor: hackable engine via EngineCore trait + strategy interfaces by @wseaton in #3
  • feat: latency trace record/replay (guidellm ingest + engine-core recording tap) by @wseaton in #4
  • Multimodal trace capture + byte-identical replay (gemma-4/3, diffusiongemma) by @wseaton in #5
  • Trace capture/replay, multi-version vLLM conformance, and release pipeline by @wseaton in #6

New Contributors

Full Changelog: https://github.com/neuralmagic/inference-simulator-rs/commits/v0.1.0

Contributors

wseaton
Loading