[6/n] Migrate activation kernels, gptq, gguf, non cutlass w8a8 to libtorch stable ABI (continued) (#42663)

Signed-off-by: Mikayla Gawarecki <mikaylagawarecki@gmail.com>
Signed-off-by: Chris Leonard <chleonar@redhat.com>
Co-authored-by: Mikayla Gawarecki <mikaylagawarecki@gmail.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
This commit is contained in:
Chris Leonard
2026-05-20 00:18:12 -07:00
committed by GitHub
co-authored by Mikayla Gawarecki Shengqi Chen
parent 40651c0207
commit 07aeaf9d4d
28 changed files with 810 additions and 639 deletions
+1 -3
View File
@@ -1045,9 +1045,7 @@ if _is_cpu():
if _build_custom_ops():
ext_modules.append(CMakeExtension(name="vllm._C"))
# also _is_hip() once https://github.com/vllm-project/vllm/issues/35163 is
# fixed
if _is_cuda():
if _is_cuda() or _is_hip():
ext_modules.append(CMakeExtension(name="vllm._C_stable_libtorch"))
package_data = {