Merge branch 'v0.6.3.post1-dev'

ad385667 · zhuwenwen · be0967c1 · 903593d3 · ad385667 · ad385667
Commit ad385667 authored Oct 23, 2024 by zhuwenwen
20 changed files
--- a/SECURITY.md
+++ b/SECURITY.md
+# Security Policy
+## Reporting a Vulnerability
+If you believe you have found a security vulnerability in vLLM, we encourage you to let us know right away. We will investigate all legitimate reports and do our best to quickly fix the problem.
+Please report security issues privately using [the vulnerability submission form](https://github.com/vllm-project/vllm/security/advisories/new).
+---
+Please see [PyTorch's Security Policy](https://github.com/pytorch/pytorch/blob/main/SECURITY.md) for more information and recommendations on how to securely interact with models.
--- a/benchmarks/backend_request_func.py
+++ b/benchmarks/backend_request_func.py
--- a/benchmarks/benchmark_latency.py
+++ b/benchmarks/benchmark_latency.py
--- a/benchmarks/benchmark_prefix_caching.py
+++ b/benchmarks/benchmark_prefix_caching.py
--- a/benchmarks/benchmark_prioritization.py
+++ b/benchmarks/benchmark_prioritization.py
--- a/benchmarks/benchmark_serving.py
+++ b/benchmarks/benchmark_serving.py
--- a/benchmarks/benchmark_throughput.py
+++ b/benchmarks/benchmark_throughput.py
--- a/benchmarks/cutlass_benchmarks/w8a8_benchmarks.py
+++ b/benchmarks/cutlass_benchmarks/w8a8_benchmarks.py
--- a/benchmarks/kernels/benchmark_layernorm.py
+++ b/benchmarks/kernels/benchmark_layernorm.py
--- a/benchmarks/kernels/benchmark_machete.py
+++ b/benchmarks/kernels/benchmark_machete.py
--- a/benchmarks/kernels/benchmark_moe.py
+++ b/benchmarks/kernels/benchmark_moe.py
--- a/benchmarks/kernels/benchmark_paged_attention.py
+++ b/benchmarks/kernels/benchmark_paged_attention.py
--- a/benchmarks/kernels/benchmark_quant.py
+++ b/benchmarks/kernels/benchmark_quant.py
--- a/benchmarks/kernels/benchmark_rope.py
+++ b/benchmarks/kernels/benchmark_rope.py
--- a/benchmarks/kernels/graph_machete_bench.py
+++ b/benchmarks/kernels/graph_machete_bench.py
--- a/benchmarks/kernels/requirements.txt
+++ b/benchmarks/kernels/requirements.txt
+pandas
\ No newline at end of file
--- a/benchmarks/kernels/weight_shapes.py
+++ b/benchmarks/kernels/weight_shapes.py
--- a/benchmarks/launch_tgi_server.sh
+++ b/benchmarks/launch_tgi_server.sh
--- a/benchmarks/overheads/benchmark_hashing.py
+++ b/benchmarks/overheads/benchmark_hashing.py
--- a/cmake/cpu_extension.cmake
+++ b/cmake/cpu_extension.cmake