Commit 638dfcb
committed
fix: make NVIDIA CUDA targets shared to prevent segfault
Change `infiniop-nvidia`, `infinirt-nvidia`, `infiniccl-nvidia` from
static to shared libraries so that `nvcc` performs proper CUDA device
linking within each `.so`. When these were static archives, `g++`
linked them into downstream shared libraries without device linking,
corrupting `.nv_fatbin` registration and causing segfaults in
`__cudaRegisterLinkedBinary` during `dlopen`.
Also replace no-op `on_install` with proper `set_installdir` for all
four NVIDIA targets (including `flash-attn-nvidia`).1 parent c3e0c69 commit 638dfcb
1 file changed
+7
-7
lines changed| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
14 | 14 | | |
15 | 15 | | |
16 | 16 | | |
17 | | - | |
| 17 | + | |
18 | 18 | | |
19 | | - | |
| 19 | + | |
20 | 20 | | |
21 | 21 | | |
22 | 22 | | |
| |||
101 | 101 | | |
102 | 102 | | |
103 | 103 | | |
104 | | - | |
| 104 | + | |
105 | 105 | | |
106 | | - | |
| 106 | + | |
107 | 107 | | |
108 | 108 | | |
109 | 109 | | |
| |||
124 | 124 | | |
125 | 125 | | |
126 | 126 | | |
127 | | - | |
| 127 | + | |
128 | 128 | | |
129 | | - | |
| 129 | + | |
130 | 130 | | |
131 | 131 | | |
132 | 132 | | |
| |||
202 | 202 | | |
203 | 203 | | |
204 | 204 | | |
205 | | - | |
| 205 | + | |
206 | 206 | | |
207 | 207 | | |
0 commit comments