Add support for Qwen3 MoE+GPTQ

2025-11-15 20:14:45 +08:00
parent b296c44ae0
commit 8152e24cb2
35 changed files with 6468 additions and 574 deletions
--- a/vllm/_utils/mem_constants.py
+++ b/vllm/_utils/mem_constants.py
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+MB_bytes = 1_000_000
+"""The number of bytes in one megabyte (MB)."""
+
+MiB_bytes = 1 << 20
+"""The number of bytes in one mebibyte (MiB)."""
+
+GB_bytes = 1_000_000_000
+"""The number of bytes in one gigabyte (GB)."""
+
+GiB_bytes = 1 << 30
+"""The number of bytes in one gibibyte (GiB)."""