[inference] add reference and fix some bugs (#4937)

* add reference and fix some bugs * update gptq init --------- Co-authored-by: Xu Kai <xukai16@foxamil.com>
2025-09-14 21:51:57 +00:00 · 2023-10-20 13:39:34 +08:00
parent b8e770c832
commit 785802e809
7 changed files with 24 additions and 10 deletions
--- a/colossalai/kernel/triton/gptq_triton.py
+++ b/colossalai/kernel/triton/gptq_triton.py
@@ -267,6 +267,7 @@ def cai_gptq_matmul_248_kernel(
    tl.store(c_ptrs, accumulator, mask=c_mask)


+# Adapted from AutoGPTQ auto_gptq: https://github.com/PanQiWei/AutoGPTQ
@autotune(
    configs=[
        triton.Config(