merge v0.4.0

7c4f76e3 · zhuwenwen · 2da0dd3e · 51c31bc1 · 7c4f76e3 · 7c4f76e3
Commit 7c4f76e3 authored Apr 15, 2024 by zhuwenwen
20 changed files
--- a/vllm/attention/layer.py
+++ b/vllm/attention/layer.py
--- a/vllm/attention/ops/__init__.py
+++ b/vllm/attention/ops/__init__.py
--- a/vllm/attention/ops/paged_attn.py
+++ b/vllm/attention/ops/paged_attn.py
--- a/vllm/model_executor/layers/triton_kernel/prefix_prefill.py
+++ b/vllm/model_executor/layers/triton_kernel/prefix_prefill.py
--- a/vllm/attention/selector.py
+++ b/vllm/attention/selector.py
--- a/vllm/block.py
+++ b/vllm/block.py
--- a/vllm/config.py
+++ b/vllm/config.py
--- a/vllm/core/block/block_table.py
+++ b/vllm/core/block/block_table.py
--- a/vllm/core/block/common.py
+++ b/vllm/core/block/common.py
--- a/vllm/core/block/cpu_gpu_block_allocator.py
+++ b/vllm/core/block/cpu_gpu_block_allocator.py
--- a/vllm/core/block/interfaces.py
+++ b/vllm/core/block/interfaces.py
--- a/vllm/core/block/naive_block.py
+++ b/vllm/core/block/naive_block.py
--- a/vllm/core/block/prefix_caching_block.py
+++ b/vllm/core/block/prefix_caching_block.py
--- a/vllm/core/block_manager.py
+++ b/vllm/core/block_manager.py
--- a/vllm/core/block_manager_v2.py
+++ b/vllm/core/block_manager_v2.py
--- a/vllm/core/evictor.py
+++ b/vllm/core/evictor.py
--- a/vllm/core/interfaces.py
+++ b/vllm/core/interfaces.py
--- a/vllm/core/scheduler.py
+++ b/vllm/core/scheduler.py
--- a/vllm/engine/arg_utils.py
+++ b/vllm/engine/arg_utils.py
--- a/vllm/engine/async_llm_engine.py
+++ b/vllm/engine/async_llm_engine.py