Merge tag 'v0.8.4' into v0.8.4-dev

31330101 · zhuwenwen · e8933c34 · dc1b4a6f · 31330101 · 31330101
Commit 31330101 authored Apr 16, 2025 by zhuwenwen
20 changed files
--- a/vllm/model_executor/layers/fused_moe/layer.py
+++ b/vllm/model_executor/layers/fused_moe/layer.py
--- a/vllm/model_executor/layers/linear.py
+++ b/vllm/model_executor/layers/linear.py
--- a/vllm/model_executor/layers/mamba/mamba2_metadata.py
+++ b/vllm/model_executor/layers/mamba/mamba2_metadata.py
--- a/vllm/model_executor/layers/mamba/mamba_mixer2.py
+++ b/vllm/model_executor/layers/mamba/mamba_mixer2.py
--- a/vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py
+++ b/vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py
--- a/vllm/model_executor/layers/mamba/ops/ssd_combined.py
+++ b/vllm/model_executor/layers/mamba/ops/ssd_combined.py
--- a/vllm/model_executor/layers/mamba/ops/ssd_state_passing.py
+++ b/vllm/model_executor/layers/mamba/ops/ssd_state_passing.py
--- a/vllm/model_executor/layers/pooler.py
+++ b/vllm/model_executor/layers/pooler.py
--- a/vllm/model_executor/layers/quantization/__init__.py
+++ b/vllm/model_executor/layers/quantization/__init__.py
--- a/vllm/model_executor/layers/quantization/blockwise_int8.py
+++ b/vllm/model_executor/layers/quantization/blockwise_int8.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
--- a/vllm/model_executor/layers/quantization/fp8.py
+++ b/vllm/model_executor/layers/quantization/fp8.py
--- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py
+++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py
--- a/vllm/model_executor/layers/quantization/moe_wna16.py
+++ b/vllm/model_executor/layers/quantization/moe_wna16.py
--- a/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py
+++ b/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py
--- a/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py
+++ b/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py
--- a/vllm/model_executor/layers/quantization/torchao.py
+++ b/vllm/model_executor/layers/quantization/torchao.py
--- a/vllm/model_executor/layers/quantization/utils/int8_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/int8_utils.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils.py