Rain-Bus/nano-vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
48 Commits 1 Branch 0 Tags
bf99453d90aab3506c93edf182b98986b0fd43c6
Commit Graph

7 Commits

Author SHA1 Message Date
Anai-Guo bf99453d90 fix RowParallelLinear weight_loader crash when bias is enabled 
When RowParallelLinear has bias=True, the weight_loader crashes with an
IndexError because it calls param_data.size(tp_dim) where tp_dim=1, but
the bias tensor is 1D and only has dimension 0.

The bias in RowParallelLinear is not sharded (all ranks hold the full
bias, only rank 0 applies it), so skip the sharding logic for 1D params.

Fixes GeeeekExplorer/nano-vllm#125
 2026-04-12 23:10:52 -07:00
GeeeekExplorer df99418f7d simplify 2025-08-31 20:02:51 +08:00
GeeeekExplorer 38baf0bbe4 remove assert shape 2025-06-27 23:00:30 +08:00
GeeeekExplorer cde3fc22c2 simplify 2025-06-21 17:19:15 +08:00
cheunglei 53b3ef2e32 support tensor parallel 2025-06-15 01:31:24 +08:00
GeeeekExplorer 08c84ec08d multi file loader 2025-06-12 01:00:09 +08:00
GeeeekExplorer a5a4909e6a init commit 2025-06-10 00:27:01 +08:00