Merge tag 'v0.6.5' into v0.6.5-dev

4d3a2c28 · zhuwenwen · 92ec5d8e · 2d1b9baa · 4d3a2c28 · 4d3a2c28
Commit 4d3a2c28 authored Dec 30, 2024 by zhuwenwen
20 changed files
--- a/vllm/attention/ops/ipex_attn.py
+++ b/vllm/attention/ops/ipex_attn.py
--- a/vllm/attention/ops/prefix_prefill.py
+++ b/vllm/attention/ops/prefix_prefill.py
--- a/vllm/attention/selector.py
+++ b/vllm/attention/selector.py
--- a/vllm/beam_search.py
+++ b/vllm/beam_search.py
--- a/vllm/benchmarks/benchmark_throughput.py
+++ b/vllm/benchmarks/benchmark_throughput.py
--- a/vllm/compilation/backends.py
+++ b/vllm/compilation/backends.py
--- a/vllm/compilation/counter.py
+++ b/vllm/compilation/counter.py
--- a/vllm/compilation/decorators.py
+++ b/vllm/compilation/decorators.py
--- a/vllm/compilation/fix_functionalization.py
+++ b/vllm/compilation/fix_functionalization.py
--- a/vllm/compilation/fusion.py
+++ b/vllm/compilation/fusion.py
--- a/vllm/compilation/fx_utils.py
+++ b/vllm/compilation/fx_utils.py
--- a/vllm/compilation/inductor_pass.py
+++ b/vllm/compilation/inductor_pass.py
--- a/vllm/compilation/monitor.py
+++ b/vllm/compilation/monitor.py
--- a/vllm/compilation/multi_output_match.py
+++ b/vllm/compilation/multi_output_match.py
--- a/vllm/compilation/pass_manager.py
+++ b/vllm/compilation/pass_manager.py
--- a/vllm/compilation/reshapes.py
+++ b/vllm/compilation/reshapes.py
--- a/vllm/compilation/vllm_inductor_pass.py
+++ b/vllm/compilation/vllm_inductor_pass.py
--- a/vllm/compilation/wrapper.py
+++ b/vllm/compilation/wrapper.py
--- a/vllm/config.py
+++ b/vllm/config.py
--- a/vllm/core/block/block_table.py
+++ b/vllm/core/block/block_table.py