A CUDA 13.x build of llama.cpp needs a driver that runs CUDA 13.x
CI / test (push) Failing after 9m48s
CI / test (push) Failing after 9m48s
The release carries some GPUs' code as PTX, which the driver compiles, and a driver older than the toolkit refuses it at the first kernel, after the build has already listed the GPU. On cuda01 (Turing, driver 615 = CUDA 13.4) b12606's CUDA 13.5 build installed and then aborted loading Inkling 2 Mini with "the provided PTX was compiled with an unsupported toolchain". The driver's CUDA, which NVML already reports per GPU, is now carried on the host and the CUDA 13.x candidate is passed over for CUDA 12.8 when the driver is older. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
09ebe77513
commit
6765d430d8
5 files changed
+65
-13
No files matched your search
@@ -289,6 +289,21 @@ func TestTheBuildFollowsTheHardware(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// Found on cuda01 (Turing, driver 615, which runs CUDA 13.4): b12606's
|
||||
// CUDA 13.5 build listed the GPU, then failed its first kernel with "the
|
||||
// provided PTX was compiled with an unsupported toolchain".
|
||||
turing := discovery.Host{Arch: "amd64", NVIDIADriver: "615.71.09", MinComputeCapability: 7.5}
|
||||
for _, c := range []struct {
|
||||
driverCUDA string
|
||||
want string
|
||||
}{{"13.4", "cuda-12.8"}, {"13.5", "cuda-13.5"}, {"14.0", "cuda-13.5"}, {"", "cuda-13.5"}} {
|
||||
turing.DriverCUDA = c.driverCUDA
|
||||
got, err := llamaCppCandidates("b12606", "", turing)
|
||||
if err != nil || got[0].Variant != c.want {
|
||||
t.Errorf("driver for CUDA %q: %+v, %v; want %s first", c.driverCUDA, got, err, c.want)
|
||||
}
|
||||
}
|
||||
|
||||
slow := ubuntu
|
||||
slow.CPUFlags = nil
|
||||
st := (&Installer{Host: slow}).ready(Status{}, Build{CPUFlags: []string{"avx2"}}, "/x/llama-server", "")
|
||||
|
||||
Reference in new issue
Block a user