fix(sglang): bound cuda-tile below the 1.6 prereleases (#11320)

Every CUDA sglang image failed in the 2026-08-02 full-matrix rebuild:
-gpu-nvidia-cuda-12-sglang, -gpu-nvidia-cuda-13-sglang and
-nvidia-l4t-cuda-13-arm64-sglang, all with the same build error.

    Building cuda-tile==1.6.0rc3
    x Failed to build `cuda-tile==1.6.0rc3`
      ModuleNotFoundError: No module named 'wheel_stub'
    hint: `cuda-tile` (v1.6.0rc3) was included because `sglang` (v0.5.16)
          depends on `flashinfer-python` (v0.6.14) which depends on `cuda-tile`

This is the failure mode requirements-cublas1{2,3}-after.txt already
carries an nvidia-modelopt bound for, arriving through a different
package. install.sh passes a global --prerelease=allow, which is
load-bearing for flash-attn-4, so an unbounded dependency resolves to a
prerelease; cuda-tile 1.6.0rc3's build backend imports wheel_stub without
declaring it in build-system.requires; --no-build-isolation means nothing
provides it, and the build dies.

Nothing in this repo changed. cuda-tile published 1.6.0rc1 and rc3 and
the weekly cron picked them up, which is the drift that job exists to
catch.

Bound the one package rather than dropping the global flag, matching the
existing precedent. 1.5.0 is the newest stable release, so <1.6 takes the
last good one. l4t13 gets the same bound: it installs plain sglang rather
than sglang[all], but flashinfer-python is a dependency of both.

NOT VERIFIED LOCALLY: reproducing this needs a CUDA docker build, which
this machine cannot run. The diagnosis is from the CI log and the
resolver's own hint, and the change follows a fix already proven in these
same files. CI on this PR is the check that matters.


Assisted-by: Claude Code:claude-opus-5 [Read] [Edit] [Bash]

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>

backend/python/sglang/requirements-cublas12-after.txt

@@ -15,3 +15,12 @@ sglang[all]>=0.5.11
 # load-bearing for flash-attn-4, and this is the narrower change. Raise the
 # bound once 0.46.0 final ships.
 nvidia-modelopt<0.46
+
+# Same failure mode as the nvidia-modelopt bound above, via a different
+# package. sglang -> flashinfer-python -> cuda-tile, unbounded, and the
+# global --prerelease=allow resolves it to 1.6.0rc3, whose build backend
+# imports wheel_stub without declaring it in build-system.requires. With
+# --no-build-isolation nothing installs it and the build dies with
+# "No module named 'wheel_stub'". 1.5.0 is the newest stable release.
+# Raise the bound once 1.6.0 final ships.
+cuda-tile<1.6

backend/python/sglang/requirements-cublas13-after.txt

@@ -15,3 +15,12 @@ sglang[all]>=0.5.11
 # load-bearing for flash-attn-4, and this is the narrower change. Raise the
 # bound once 0.46.0 final ships.
 nvidia-modelopt<0.46
+
+# Same failure mode as the nvidia-modelopt bound above, via a different
+# package. sglang -> flashinfer-python -> cuda-tile, unbounded, and the
+# global --prerelease=allow resolves it to 1.6.0rc3, whose build backend
+# imports wheel_stub without declaring it in build-system.requires. With
+# --no-build-isolation nothing installs it and the build dies with
+# "No module named 'wheel_stub'". 1.5.0 is the newest stable release.
+# Raise the bound once 1.6.0 final ships.
+cuda-tile<1.6

backend/python/sglang/requirements-l4t13-after.txt

@@ -13,3 +13,12 @@
 # FunctionCallParser, ReasoningParser); the [all] extras are optional
 # accelerators not required at import time.
 sglang>=0.5.11
+
+# Same failure mode the cublas profiles carry an nvidia-modelopt bound for,
+# reached through a different package. sglang -> flashinfer-python ->
+# cuda-tile, unbounded, and the global --prerelease=allow resolves it to
+# 1.6.0rc3, whose build backend imports wheel_stub without declaring it in
+# build-system.requires. With --no-build-isolation nothing installs it and
+# the build dies with "No module named 'wheel_stub'". 1.5.0 is the newest
+# stable release. Raise the bound once 1.6.0 final ships.
+cuda-tile<1.6