Merge tag 'v0.18.1rc0' into v0.18.1rc0-ori

0da93439 · zhuwenwen · 25f2f756 · 298e5108 · 0da93439 · 0da93439
Commit 0da93439 authored Mar 26, 2026 by zhuwenwen
16 changed files
--- a/vllm/v1/worker/gpu/attn_utils.py
+++ b/vllm/v1/worker/gpu/attn_utils.py
--- a/vllm/v1/worker/gpu/block_table.py
+++ b/vllm/v1/worker/gpu/block_table.py
--- a/vllm/v1/worker/gpu/kv_connector.py
+++ b/vllm/v1/worker/gpu/kv_connector.py
--- a/vllm/v1/worker/gpu/model_runner.py
+++ b/vllm/v1/worker/gpu/model_runner.py
--- a/vllm/v1/worker/gpu/model_states/default.py
+++ b/vllm/v1/worker/gpu/model_states/default.py
--- a/vllm/v1/worker/gpu/model_states/interface.py
+++ b/vllm/v1/worker/gpu/model_states/interface.py
--- a/vllm/v1/worker/gpu/spec_decode/eagle/speculator.py
+++ b/vllm/v1/worker/gpu/spec_decode/eagle/speculator.py
--- a/vllm/v1/worker/gpu/spec_decode/rejection_sampler.py
+++ b/vllm/v1/worker/gpu/spec_decode/rejection_sampler.py
--- a/vllm/v1/worker/gpu/states.py
+++ b/vllm/v1/worker/gpu/states.py
--- a/vllm/v1/worker/gpu_input_batch.py
+++ b/vllm/v1/worker/gpu_input_batch.py
--- a/vllm/v1/worker/gpu_model_runner.py
+++ b/vllm/v1/worker/gpu_model_runner.py
--- a/vllm/v1/worker/gpu_ubatch_wrapper.py
+++ b/vllm/v1/worker/gpu_ubatch_wrapper.py
--- a/vllm/v1/worker/gpu_worker.py
+++ b/vllm/v1/worker/gpu_worker.py
--- a/vllm/v1/worker/mamba_utils.py
+++ b/vllm/v1/worker/mamba_utils.py
--- a/vllm/v1/worker/utils.py
+++ b/vllm/v1/worker/utils.py
--- a/vllm/v1/worker/worker_base.py
+++ b/vllm/v1/worker/worker_base.py