AITER v0.1.14-rc0

First release candidate for v0.1.14, cut from main at:
  7595896 [Triton] [ATOM] DSV4 fusions phase 1 (#3057)

Validation (mi355-gpu-15 + mi355-gpu-9, GSM8K 3-shot flexible-extract):
  DSR1               PASS
  MiniMax-M2.5       PASS
  Qwen3-235B-A22B    PASS
  GLM-5-FP8          PASS
  Kimi-K2.5-MXFP4    PASS (0.9303, requires ATOM with PR #670 / kwargs upgrade)

Cherry-picks deferred to rc1 (per Markus must-list):
  #3163 minimax fused qknorm+allreduce
  #3189 (pending review) grid-strided loop on top of #3163

[Bugfix] Suppress pandas FutureWarning and fix pybind11 type hint mis…

…match (#2980)

- aiter/jit/core.py: filter out empty DataFrames before pd.concat to
  avoid FutureWarning about empty/all-NA dtype inference
- csrc/include/rocm_ops.hpp: add py::arg(...) to ROPE 1c/2c
  cached_positions(_offsets) fwd bindings and wv_splitk_small_fp16_bf16
  so pybind11 doc strings expose real parameter names instead of
  arg0/arg1/..., eliminating the spurious "type hints mismatch" warnings

[Bugfix] Suppress pandas FutureWarning and fix pybind11 type hint mis…

…match (#2980)

- aiter/jit/core.py: filter out empty DataFrames before pd.concat to
  avoid FutureWarning about empty/all-NA dtype inference
- csrc/include/rocm_ops.hpp: add py::arg(...) to ROPE 1c/2c
  cached_positions(_offsets) fwd bindings and wv_splitk_small_fp16_bf16
  so pybind11 doc strings expose real parameter names instead of
  arg0/arg1/..., eliminating the spurious "type hints mismatch" warnings

fix splitk buffer dispatch (#3050)

Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>

AITER v0.1.13-rc3

rc2 + #3049 (do not swallow import errors on Linux)

v0.1.13-rc2

rc1 + #2879 (DI/SA blocker) + #3004 (Silo bulk configs) + #3005 (Silo bulk kernels) + #3024 (Silo missing configs) + #2983 (MLA nhead=32 crash fix)

revert gptoss tuned config (#2904)

---------

Co-authored-by: zhuyuhua-v <yuhzhu@amd.com>

revert gptoss tuned config (#2904)

---------

Co-authored-by: zhuyuhua-v <yuhzhu@amd.com>

Merge pull request #2874 from ROCm/pensun/post2-with-2645

[release/v0.1.12] Cherry-pick #2645 (multi-arch CK GEMM dispatch) + SynchronizedCache backport for v0.1.12.post2

Prepare v0.1.12 release

- Add release/** branch trigger to all CI workflows
- Fix release workflow validation and edge cases
- Add auto-release workflow with prebuild validation and S3 upload
- Add release process documentation and checklist
- Add v0.1.12 release notes (334 commits categorized)
- Cherry-pick #2671: fix GEMM scale masking for issue #2656
- Revert problematic GEMM config for DSR1-MXFP4 accuracy