Skip to content
This repository has been archived by the owner on Oct 11, 2024. It is now read-only.

v0.5.0

Latest
Compare
Choose a tag to compare
@dhuangnm dhuangnm released this 24 Jun 14:12
· 29 commits to main since this release
046eb08

Key Features

This is based on upstream vllm = v0.5.0.post

What's Changed

  • bump up version to 0.5.0 by @dhuangnm in #278
  • update publish.yml by @andy-neuma in #280
  • fix a minor bug for docker build by @dhuangnm in #281
  • update publish.yml by @andy-neuma in #282
  • [CI/Build] Verify licenses by @derekk-nm in #272
  • strip binaries by @dhuangnm in #283
  • only run multi-gpu for python 3.10.12 by @andy-neuma in #284
  • add more models, new num_logprobs by @derekk-nm in #285
  • upload NIGHTLY assets to GCP by @andy-neuma in #286
  • GCP test runners by @andy-neuma in #275
  • Add nightly tag by @dhuangnm in #287
  • Upstream sync 2024 06 08 by @robertgshaw2-neuralmagic in #288
  • [Rel Eng] Update Nightly Workflow To Use Proper Skip List by @robertgshaw2-neuralmagic in #296
  • [Rel Eng] Upstream sync 2024 06 11 by @robertgshaw2-neuralmagic in #298
  • use nm-pypi service account by @andy-neuma in #300
  • default nvcc_threads to 8 in order to reduce build execution time by @derekk-nm in #304
  • Upstream sync 2024 06 12 by @robertgshaw2-neuralmagic in #302
  • Fix docker image build issue by @dhuangnm in #305
  • Remote push refactor by @robertgshaw2-neuralmagic in #297
  • Update nm-nightly.yml by @derekk-nm in #308
  • Use shared actions by @dbarbuzzi in #309
  • enble tests that require C compiler by @andy-neuma in #310
  • [ CI ] Fix Failing Test Server Logprobs (tolerance tweak) by @robertgshaw2-neuralmagic in #312
  • [ CI ] Fix Failing Magic Wand Test by @robertgshaw2-neuralmagic in #311
  • Add githash to nm-vllm by @dhuangnm in #299
  • Upstream sync 2024 06 16 by @robertgshaw2-neuralmagic in #307
  • [ CI ] skip local_workers_clean_shutdown by @robertgshaw2-neuralmagic in #317
  • set PYTHON-3-10 job to gcp by @derekk-nm in #318
  • [Rel Eng] Dial In LM Eval Tests Phase 1 by @robertgshaw2-neuralmagic in #289
  • revert githash commit by @dhuangnm in #320
  • Pruned Readme by @robertgshaw2-neuralmagic in #313
  • Force-disable upstream tracking by @dbarbuzzi in #321
  • [ README ] Update README.md by @robertgshaw2-neuralmagic in #323

Full Changelog: 0.4.0...0.5.0