{"package":"vllm-tpu","ecosystem":"pypi","latest_version":"0.18.0","description":"A high-throughput and memory-efficient inference and serving engine for LLMs","license":"Apache-2.0","license_risk":"permissive","commercial_use_notes":"Permissive: commercial closed-source use OK; preserve the copyright notice.","homepage":"https://pypi.org/project/vllm-tpu/","repository":"https://github.com/vllm-project/vllm","downloads_weekly":13846,"health":{"score":81,"risk":"low","breakdown":{"maintenance":25,"popularity":10,"security":25,"maturity":9,"community":12},"deprecated":false,"max_score":100},"vulnerabilities":{"count":0,"critical":0,"high":0,"medium":0,"low":0,"details":[]},"versions":{"latest":"0.18.0","total_count":19,"recent":["0.9.3","0.9.4.dev0","0.10.1.1","0.11.1rc1","0.11.1rc2","0.11.1rc3","0.11.1","0.11.2rc1","0.12.0rc1","0.12.0rc2","0.12.0","0.13.2rc1","0.13.2rc3","0.13.2rc4","0.13.2rc4.post6","0.13.2.post6","0.13.3","0.18.0rc1","0.18.0"]},"metadata":{"deprecated":false,"deprecated_message":null,"maintainers_count":1,"first_published":null,"last_published":"2026-04-20T16:48:29.407312Z","dependencies_count":89,"dependencies":["regex","cachetools","psutil","sentencepiece","numpy","requests>=2.26.0","tqdm","blake3","py-cpuinfo","transformers<5,>=4.56.0","tokenizers>=0.21.1","protobuf!=6.30.*,!=6.31.*,!=6.32.*,!=6.33.0.*,!=6.33.1.*,!=6.33.2.*,!=6.33.3.*,!=6.33.4.*,>=5.29.6","fastapi[standard]>=0.115.0","aiohttp>=3.13.3","openai>=2.0.0","pydantic>=2.12.0","prometheus_client>=0.18.0","pillow","prometheus-fastapi-instrumentator>=7.0.0","tiktoken>=0.6.0","lm-format-enforcer==0.11.3","llguidance<1.4.0,>=1.3.0; platform_machine == \"x86_64\" or platform_machine == \"arm64\" or platform_machine == \"aarch64\" or platform_machine == \"s390x\" or platform_machine == \"ppc64le\"","outlines_core==0.2.11","diskcache==5.6.3","lark==1.2.2","xgrammar<1.0.0,>=0.1.32; platform_machine == \"x86_64\" or platform_machine == \"aarch64\" or platform_machine == \"arm64\" or platform_machine == \"s390x\" or platform_machine == \"ppc64le\"","typing_extensions>=4.10","filelock>=3.16.1","partial-json-parser","pyzmq>=25.0.0","msgspec","gguf>=0.17.0","mistral_common[image]>=1.10.0","opencv-python-headless>=4.13.0","pyyaml","six>=1.16.0; python_version > \"3.11\"","setuptools<81.0.0,>=77.0.3; python_version > \"3.11\"","einops","compressed-tensors==0.14.0.1","depyf==0.20.0","cloudpickle","watchfiles","python-json-logger","ninja","pybase64","cbor2","ijson","setproctitle","openai-harmony>=0.0.3","anthropic>=0.71.0","model-hosting-container-standards<1.0.0,>=0.1.13","mcp","opentelemetry-sdk>=1.27.0","opentelemetry-api>=1.27.0","opentelemetry-exporter-otlp>=1.27.0","opentelemetry-semantic-conventions-ai>=0.4.1","cmake>=3.26.1","packaging>=24.2","setuptools-scm>=8","wheel","jinja2>=3.1.6","ray[default]","ray[data]","setuptools==78.1.0","nixl==0.3.0","tpu-inference==0.18.0","zentorch; extra == \"zen\"","pandas; extra == \"bench\"","matplotlib; extra == \"bench\"","seaborn; extra == \"bench\"","datasets; extra == \"bench\"","scipy; extra == \"bench\"","plotly; extra == \"bench\"","tensorizer==2.10.1; extra == \"tensorizer\"","fastsafetensors>=0.2.2; extra == \"fastsafetensors\"","instanttensor>=0.1.5; extra == \"instanttensor\"","runai-model-streamer[azure,gcs,s3]>=0.15.7; extra == \"runai\"","av; extra == \"audio\"","resampy; extra == \"audio\"","scipy; extra == \"audio\"","soundfile; extra == \"audio\"","mistral_common[audio]; extra == \"audio\"","petit-kernel; extra == \"petit-kernel\"","helion==0.3.2; extra == \"helion\"","smg-grpc-servicer[vllm]>=0.5.0; extra == \"grpc\"","opentelemetry-sdk>=1.26.0; extra == \"otel\"","opentelemetry-api>=1.26.0; extra == \"otel\"","opentelemetry-exporter-otlp>=1.26.0; extra == \"otel\"","opentelemetry-semantic-conventions-ai>=0.4.1; extra == \"otel\""]},"github_stats":{"stars":78944,"forks":16380,"open_issues":4754,"is_archived":false,"pushed_at":"2026-05-04T00:39:11Z","subscribers_count":535},"bundle":null,"typescript":null,"known_issues":{"bugs_count":0,"bugs_severity":{},"status_breakdown":{},"link":null,"scope":"none"},"historical_compromise":null,"recommendation":{"action":"safe_to_use","issues":[],"use_version":"0.18.0","version_hint":null,"summary":"vllm-tpu@0.18.0 is safe to use (health: 81/100)"},"version_scoped":null,"_meta":{"endpoint":"check","tier":"full","philosophy":"DepScope is free. Use the cheapest endpoint that answers your real question.","cheaper_alternatives":[{"endpoint":"/api/exists/pypi/vllm-tpu","tokens_estimated":12,"use_when":"you only need to know if the package exists (hallucination guard)"},{"endpoint":"/api/health/pypi/vllm-tpu","tokens_estimated":80,"use_when":"you only need a 0-100 score for go/no-go (>=70 = safe)"},{"endpoint":"/api/prompt/pypi/vllm-tpu","tokens_estimated":280,"use_when":"you want a plain-text LLM-friendly brief instead of JSON"},{"endpoint":"POST /api/check_bulk","tokens_estimated":60,"use_when":"you have 5+ packages to check; sends one round-trip instead of N"}],"docs":"https://depscope.dev/integrate","hint_bulk":"You've called /api/check 21 times in 60s. Save bandwidth + tokens with POST /api/check_bulk (1 round-trip for N pkgs)."},"requested_version":null,"_cache":"miss","_response_ms":1024,"_powered_by":"depscope.dev — free package intelligence for AI agents","typosquat":{"is_suspected":false},"maintainer_trust":{"available":false},"malicious":{"is_malicious":false},"scorecard":{"available":false},"quality":{"available":false},"version_history_summary":{"total_versions":19,"first_release_age_days":null,"last_release_days_ago":13,"avg_days_between_releases":null,"release_velocity":"active"}}