62 labels
Sort
Sort
-
aardvark
-
bug
Something isn't working -
build-docs
-
ci/build
-
ci-failure
Issue about an unexpected test failure in CI -
claude-code-assisted
-
closed-as-slop
Pull request determined to be low effort and agent generated -
codex
-
cpu
Related to CPU backends -
deepseek
Related to DeepSeek models -
dependencies
Pull requests that update a dependency file -
dflash
-
documentation
Improvements or additions to documentation -
DSv4
-
fb-exported
-
feature request
New feature or request -
frontend
-
github_actions
Pull requests that update GitHub Actions code -
good first issue
Good for newcomers -
gpt-oss
Related to GPT-OSS models -
help wanted
Extra attention is needed -
installation
Installation problems -
intel-gpu
Related to Intel GPU -
k3
-
keep-open
Prevents stale label being applied -
kimi
-
kv-connector
-
llama
Related to Llama models -
meta-exported
-
mistral
Related to Mistral models -
model-bash
-
mrv1-only
Issues/PRs which apply only to Model Runner V2 (not applicable to Model Runner V2) -
multi-modality
Related to multi-modality (#4194) -
needs-rebase
-
needs reproduction
A vLLM developer is not able to reproduce this problem. Please help us reproduce it! -
needs-tests
Tests needed for this PR -
new-model
Requests to new models -
nvidia
-
performance
Performance-related issues -
quantization
-
qwen
Related to Qwen models -
ray
anything related with ray -
ready
ONLY add when PR is ready to merge/full CI is needed -
ready-run-all-tests
Trigger CI with all tests for wide-ranging PRs -
RFC
-
rl
Related to RL workflows -
rocm
Related to AMD ROCm -
rust
-
speculative-decoding
-
stale
Over 90 days of inactivity -
startup-ux
-
structured-output
-
suppress-bc-linter
-
tool-calling
-
torch.compile
-
tpu
Related to Google TPUs -
unstale
Recieved activity after being labelled stale -
usage
How to use vllm -
v1
-
v2
-
verified
Run pre-commit for new contributors without triggering other tests -
vllm-ir
vLLM IR: intermediate representation and kernel registration