commit c48df65bb123b66467d555d9d80ea4ae096e4b2c
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sun Aug 23 13:14:40 2026 +0200

dev-python/humming-kernels: depend on virtual/triton

commit 100d1dfacb3f2981a08ce51f03e5fde77505327d
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri Aug 21 10:18:09 2026 +0200

dev-python/humming-kernels: drop 0.1.6, 0.1.11

commit 0268f3eb3d79bf6e0cd40f498234c8d4be3eec6c
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri Aug 21 10:18:05 2026 +0200

dev-python/humming-kernels: add 0.1.13

commit 9d94243d4aeccabf3d66af0aad9191329cced55b
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri Aug 14 12:55:38 2026 +0200

dev-python/humming-kernels: declare wheel build dependency

The exact 0.1.12 build-system metadata requires wheel alongside setuptools and
setuptools-scm. Declare it directly rather than relying on the build frontend
environment.

commit 8d0b5c1e20ca131d84fbf37a6d08e3a64b58d478
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Tue Aug 4 11:48:32 2026 +0200

dev-python/humming-kernels: drop 0.1.4

commit ac70e5df08723ebb7adfb95fe414243078a5a4a8
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Tue Aug 4 11:46:42 2026 +0200

dev-python/humming-kernels: fix dependencies in 0.1.12

Declare the CUDA build toolchain and the package's runtime dependencies
(ninja, the CUDA toolkit, caffe2, gcc and the Python helpers) so the
offline build resolves.

commit 7bd076d78d7f24da500e91df6d3d9388a79bc692
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Tue Aug 4 11:45:19 2026 +0200

dev-python/humming-kernels: fix dependencies in 0.1.11

Declare the CUDA build toolchain and the package's runtime dependencies
(ninja, the CUDA toolkit, caffe2, gcc and the Python helpers) so the
offline build resolves.

commit f0c6d8fcb3e2303a81d8d3d92e1fc38a50cfec4f
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Tue Aug 4 11:44:00 2026 +0200

dev-python/humming-kernels: fix dependencies in 0.1.10

Declare the CUDA build toolchain and the package's runtime dependencies
(ninja, the CUDA toolkit, caffe2, gcc and the Python helpers) so the
offline build resolves.

commit 107f1c3574ff6561f8e7a3ac7b058afb9148516b
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Tue Aug 4 11:11:58 2026 +0200

dev-python/humming-kernels: restore 0.1.6

vLLM 0.24.0 pins this exact release for its optional CUDA quantization
backend. Restore it with complete CUDA runtime and build dependencies.

commit a8f1bf2e0b05457f19bae80514a5398d0027b13d
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sat Aug 1 02:17:56 2026 +0200

dev-python/humming-kernels: drop 0.1.2, 0.1.7

Superseded; retention keeps the last two (0.1.11, 0.1.12) plus the two
vllm consumer pins (0.1.4 for vllm-0.24.0, 0.1.10 for vllm-0.25.1/0.26.0).

commit 739bcc1946b50dcaffdcbc6810b50aa0a5a0d990
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sat Aug 1 02:17:50 2026 +0200

dev-python/humming-kernels: add 0.1.12

Upstream dropped pyelftools from its requirements in 0.1.12 (0.1.11
declared it; 0.1.12 neither declares nor imports it), so it is removed
from RDEPEND. Other runtime dependencies are unchanged.

commit a3d36321337ebd108c8e5c1aa350c32dc3caeca3
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sun Jul 19 02:19:09 2026 +0200

dev-python/humming-kernels: add 0.1.11

commit eea247964c4fa6120a3827c45ae24e4f0fdf2274
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Wed Jul 8 10:52:52 2026 +0200

dev-python/humming-kernels: add 0.1.10

commit 48b449bc24da2a668fee7bcc0c0ccd34df7aa3f6
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri Jun 26 20:35:40 2026 +0200

dev-python/humming-kernels: drop 0.1.5, 0.1.6

commit 4b11e489a8d2fc1f1ff8a9db456c957e6b2df8a6
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri Jun 26 19:59:53 2026 +0200

dev-python/humming-kernels: add 0.1.7

commit c1c264f251147591f29f444cd71d9adddc6ca607
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sat Jun 20 10:09:53 2026 +0200

dev-python/humming-kernels: add 0.1.6

commit e62192514368500fd30be63f7c13d6a45331b8ad
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Tue Jun 16 14:28:03 2026 +0200

dev-python/humming-kernels: add 0.1.5

Prebump ahead of its consumer: vllm's latest release (0.23.0) still pins
humming-kernels[cu13]==0.1.4, so nothing pulls 0.1.5 yet. Kept current
for when a future vllm bumps the cu13 pin; the existing ~0.1.4 pin in
vllm-0.23.0[humming] is unaffected.

commit 1fc4e0437a00dcaf4e556a74d8ee6c40ed6b905a
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sun Jun 14 23:40:12 2026 +0200

dev-python/humming-kernels: new package

humming-kernels provides the `humming` Python namespace that vLLM's
quantization registry imports unconditionally on CUDA builds
(quantization/__init__.py pulls in humming.py, whose external import is
gated only by current_platform.is_cuda() with no fallback). Without it,
loading any quantized model under vllm[cuda] aborts with
ModuleNotFoundError: No module named 'humming', regardless of which
quantization method was actually requested.

JIT GEMM kernel library: a pure-Python wheel that compiles its bundled
CUDA sources at runtime via the system nvcc. 0.1.2 and 0.1.4 match the
humming-kernels pins in vllm 0.22.1 and 0.23.0 requirements/cuda.txt.