Merge branch 'v0.9.2-dev-fth' into 'v0.9.2-dev'

fuse_moe_fp8接入marlin算子 See merge request dcutoolkit/deeplearing/vllm!399

Merge branch 'v0.9.2-dev-fth' into 'v0.9.2-dev'
fuse_moe_fp8接入marlin算子 See merge request dcutoolkit/deeplearing/vllm!399
3a58da2c · zhuwenwen · a3fb334b · 3c283de3 · 3a58da2c
Commit 3a58da2c authored Feb 02, 2026 by zhuwenwen
Expand all Show whitespace changes
Inline Side-by-side

Showing with 497 additions and 2 deletions

vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe_marlin.py ...ation/compressed_tensors/compressed_tensors_moe_marlin.py +497 -2

No files found.
--- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe_marlin.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe_marlin.py