Merge tag 'v0.8.5' into v0.8.5-ori

081057de · zhuwenwen · 7cf5d5c4 · ba41cc90 · 081057de · 081057de
Commit 081057de authored Apr 29, 2025 by zhuwenwen
20 changed files
--- a/vllm/v1/serial_utils.py
+++ b/vllm/v1/serial_utils.py
--- a/vllm/v1/spec_decode/eagle.py
+++ b/vllm/v1/spec_decode/eagle.py
--- a/vllm/v1/spec_decode/metrics.py
+++ b/vllm/v1/spec_decode/metrics.py
--- a/vllm/v1/spec_decode/ngram_proposer.py
+++ b/vllm/v1/spec_decode/ngram_proposer.py
--- a/vllm/v1/structured_output/__init__.py
+++ b/vllm/v1/structured_output/__init__.py
--- a/vllm/v1/structured_output/backend_guidance.py
+++ b/vllm/v1/structured_output/backend_guidance.py
--- a/vllm/v1/structured_output/backend_types.py
+++ b/vllm/v1/structured_output/backend_types.py
--- a/vllm/v1/structured_output/backend_xgrammar.py
+++ b/vllm/v1/structured_output/backend_xgrammar.py
--- a/vllm/v1/structured_output/request.py
+++ b/vllm/v1/structured_output/request.py
--- a/vllm/v1/structured_output/utils.py
+++ b/vllm/v1/structured_output/utils.py
--- a/vllm/v1/utils.py
+++ b/vllm/v1/utils.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_worker.py
+++ b/vllm/v1/worker/gpu_worker.py
--- a/vllm/v1/worker/lora_model_runner_mixin.py
+++ b/vllm/v1/worker/lora_model_runner_mixin.py
--- a/vllm/v1/worker/tpu_model_runner.py
+++ b/vllm/v1/worker/tpu_model_runner.py
--- a/vllm/v1/worker/tpu_worker.py
+++ b/vllm/v1/worker/tpu_worker.py
--- a/vllm/worker/cache_engine.py
+++ b/vllm/worker/cache_engine.py
--- a/vllm/worker/cpu_enc_dec_model_runner.py
+++ b/vllm/worker/cpu_enc_dec_model_runner.py
--- a/vllm/worker/cpu_model_runner.py
+++ b/vllm/worker/cpu_model_runner.py