[Kernel] RFC #29630 finale: retire sglang.jit_kernel into sglang.kernels (#32072)

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

python/sglang/jit_kernel/activation.py

@@ -1,5 +0,0 @@
-"""Compatibility shim (RFC #29630 Phase 4) -> sglang.kernels.ops.activation._jit_activation."""
-
-from sglang.kernels.ops.activation import _jit_activation as _impl
-
-globals().update({k: getattr(_impl, k) for k in dir(_impl) if not k.startswith("__")})

python/sglang/jit_kernel/dsv3_fused_a_gemm.py

@@ -1,5 +0,0 @@
-"""Compatibility shim (RFC #29630 Phase 4) -> sglang.kernels.ops.gemm._jit_dsv3_fused_a_gemm."""
-
-from sglang.kernels.ops.gemm import _jit_dsv3_fused_a_gemm as _impl
-
-globals().update({k: getattr(_impl, k) for k in dir(_impl) if not k.startswith("__")})

python/sglang/jit_kernel/dsv3_router_gemm.py

@@ -1,5 +0,0 @@
-"""Compatibility shim (RFC #29630 Phase 4) -> sglang.kernels.ops.gemm._jit_dsv3_router_gemm."""
-
-from sglang.kernels.ops.gemm import _jit_dsv3_router_gemm as _impl
-
-globals().update({k: getattr(_impl, k) for k in dir(_impl) if not k.startswith("__")})

python/sglang/jit_kernel/norm.py

@@ -1,5 +0,0 @@
-"""Compatibility shim (RFC #29630 Phase 4) -> sglang.kernels.ops.layernorm._jit_norm."""
-
-from sglang.kernels.ops.layernorm import _jit_norm as _impl
-
-globals().update({k: getattr(_impl, k) for k in dir(_impl) if not k.startswith("__")})

python/sglang/jit_kernel/per_tensor_quant_fp8.py

@@ -1,5 +0,0 @@
-"""Compatibility shim (RFC #29630 Phase 4) -> sglang.kernels.ops.quantization._jit_per_tensor_quant_fp8."""
-
-from sglang.kernels.ops.quantization import _jit_per_tensor_quant_fp8 as _impl
-
-globals().update({k: getattr(_impl, k) for k in dir(_impl) if not k.startswith("__")})

python/sglang/jit_kernel/per_token_group_quant.py

@@ -1,5 +0,0 @@
-"""Compatibility shim (RFC #29630 Phase 4) -> sglang.kernels.ops.quantization._jit_per_token_group_quant."""
-
-from sglang.kernels.ops.quantization import _jit_per_token_group_quant as _impl
-
-globals().update({k: getattr(_impl, k) for k in dir(_impl) if not k.startswith("__")})

python/sglang/jit_kernel/per_token_group_quant_8bit_v2.py

@@ -1,5 +0,0 @@
-"""Compatibility shim (RFC #29630 Phase 4) -> sglang.kernels.ops.quantization._jit_per_token_group_quant_8bit_v2."""
-
-from sglang.kernels.ops.quantization import _jit_per_token_group_quant_8bit_v2 as _impl
-
-globals().update({k: getattr(_impl, k) for k in dir(_impl) if not k.startswith("__")})

python/sglang/jit_kernel/set_mla_kv_buffer.py

@@ -1,5 +0,0 @@
-"""Compatibility shim (RFC #29630 Phase 4) -> sglang.kernels.ops.kvcache._jit_set_mla_kv_buffer."""
-
-from sglang.kernels.ops.kvcache import _jit_set_mla_kv_buffer as _impl
-
-globals().update({k: getattr(_impl, k) for k in dir(_impl) if not k.startswith("__")})

python/sglang/kernels/README.md

@@ -26,7 +26,7 @@ Groups populated in this phase: `activation`, `gemm`, `kvcache`, `layernorm`,
 `moe`, `quantization`. The remaining groups (`attention`, `communication`,
 `diffusion`, `grammar`, `mamba`, `memory`, `sampling`, `spatial`,
 `speculative`) are reserved package placeholders whose implementations still
-live in `sglang.jit_kernel` / `sgl_kernel` / `triton_ops` and will migrate in
+live in `sglang.kernels.jit` / `sgl_kernel` / `triton_ops` and will migrate in
 later phases.
 
 ## How it works
@@ -104,7 +104,7 @@ What this buys (see the
 > SGLang runtime code and tests should import callable kernels from
 > `sglang.kernels.ops.*`.
 
-Implementation work can still happen in `sglang.jit_kernel` or `sgl_kernel`.
+Implementation work can still happen in `sglang.kernels.jit` or `sgl_kernel`.
 When a PR adds a new callable kernel, add a `sglang.kernels.ops.*` entry point
-for it, and avoid growing `sglang.jit_kernel` as a long-term public operator
+for it, and avoid growing `sglang.kernels.jit` as a long-term public operator
 namespace.

python/sglang/kernels/__init__.py

@@ -7,7 +7,7 @@ SGLang runtime code and tests should import callable kernels from
     from sglang.kernels.ops.activation import silu_and_mul
     from sglang.kernels.ops.kvcache import reshape_and_cache_flash
 
-Implementations still live in ``sglang.jit_kernel`` (JIT CUDA), the
+Implementations still live in ``sglang.kernels.jit`` (JIT CUDA), the
 ``sgl_kernel`` wheel (AOT CUDA/C++), Triton op modules, etc. The ``ops.*``
 functions are thin wrappers that forward to a chosen backend; the
 :data:`~sglang.kernels.registry.registry` provides an inventory of every
@@ -18,7 +18,7 @@ with a required pure-``torch`` ``forward_native`` reference and a
 ``SGLANG_FORCE_FUSED_OP_BACKEND`` global switch.
 
 Importing this package (and any ``ops.*`` group) does not import a kernel
-backend (``sgl_kernel`` / ``sglang.jit_kernel``) or trigger JIT compilation:
+backend (``sgl_kernel`` / ``sglang.kernels.jit``) or trigger JIT compilation:
 registration is metadata-only and backends are imported lazily on first call.
 This keeps the namespace usable for inventory tooling on a CPU-only box.
 """

python/sglang/kernels/fused_op.py

@@ -28,7 +28,7 @@ implementations with a single switch.
 
 Like the rest of ``sglang.kernels``, importing this module (and instantiating
 subclasses) never imports a kernel backend (``sgl_kernel`` /
-``sglang.jit_kernel``) or triggers JIT compilation; backends are imported
+``sglang.kernels.jit``) or triggers JIT compilation; backends are imported
 lazily inside the ``forward_<backend>`` methods.
 """
 

python/sglang/kernels/jit/__init__.py

@@ -1,6 +1,6 @@
 """Internal JIT home under ``sglang.kernels`` (RFC #29630).
 
-Mirrors the legacy ``sglang.jit_kernel`` tree; shared build/runtime
+Mirrors the legacy ``sglang.kernels.jit`` tree; shared build/runtime
 infrastructure lives in :mod:`sglang.kernels.jit.utils`. csrc / include /
 operators migrate here in later phases.
 """

python/sglang/kernels/jit/csrc/elementwise/fused_metadata_copy.cuh

@@ -1,6 +1,6 @@
 /*
  * Fused metadata copy kernel for DSA backend CUDA graph replay.
- * JIT-compiled version for python/sglang/jit_kernel.
+ * JIT-compiled version for python/sglang/kernels/jit.
  *
  * OVERVIEW:
  * This kernel fuses multiple tensor copy operations (cache_seqlens, cu_seqlens_k,