Merge branch 'v0.8.5.post1-dev' into v0.8.5-zero_overhead

bd363067 · lizhigong · 87ef4618 · d36deb1a · bd363067 · bd363067
Commit bd363067 authored Jun 05, 2025 by lizhigong
6 changed files
--- a/vllm/model_executor/models/llama.py
+++ b/vllm/model_executor/models/llama.py
--- a/vllm/model_executor/models/qwen.py
+++ b/vllm/model_executor/models/qwen.py
--- a/vllm/model_executor/models/qwen2.py
+++ b/vllm/model_executor/models/qwen2.py
--- a/vllm/platforms/rocm.py
+++ b/vllm/platforms/rocm.py
--- a/vllm/utils.py
+++ b/vllm/utils.py
--- a/vllm/v1/attention/backends/flash_attn.py
+++ b/vllm/v1/attention/backends/flash_attn.py