mirror of
https://github.com/FlashML-org/FreeToken.git
synced 2026-11-21 01:52:30 +08:00
* feat: add simple ROCm GPU support for RDNA3 (gfx1100-1103) - Add hip_compat.h shim mapping CUDA runtime API to HIP equivalents - Update pinned_tensor.cpp to compile under both nvcc and hipcc - Add ROCm detection in arch.py (is_rocm, get_rocm_gfx_arch, is_gfx11xx_family) - Guard NVIDIA arch checks to return None on ROCm - Skip nvcc version check in _toolchain.py when on ROCm - Add ROCm build path in setup.py (ROCM_HOME, amdhip64, --offload-arch) - Add _hip_cflags() in kernel/utils.py for JIT compilation on ROCm - Add is_rocm() and driver_hip_version() in backend.py - Add rocm-smi fallback in __main__.py for clangd generation - Add TODO(ROCm) for NCCL->RCCL, flashinfer/sgl_kernel ROCm builds, Triton autotune RDNA3 tuning, PDL equivalent, hiprtc JIT cache - Add AMD ROCm classifier in pyproject.toml * fix(rocm): fall back for single-bank fast index copy * test(rocm): cover fast index copy fallback * test(rocm): use explicit fast copy module import * fix(rocm): complete RDNA3 runtime path * fix(rocm): preserve CPU MoE implementation * build(rocm): support RDNA4 discovery and modular SDKs * fix(rocm): complete modular SDK runtime support * test(rocm): harden foundation platform contracts * fix(rocm): pin jit target and split install guide * perf(kernel): restore ROCm non-temporal index copy --------- Co-authored-by: bouclem <bouclement2012@gmail.com> Co-authored-by: Yuu <206304251+nekomario28@users.noreply.github.com> Co-authored-by: LZ-QWQ <lz1830837889@163.com>
53 lines
1.8 KiB
Python
53 lines
1.8 KiB
Python
assert __name__ == "__main__"
|
|
|
|
|
|
def generate_clangd():
|
|
import os
|
|
import subprocess
|
|
|
|
from freetoken.kernel.utils import DEFAULT_INCLUDE
|
|
from freetoken.utils import get_rocm_gfx_arch, init_logger, is_rocm
|
|
from tvm_ffi.libinfo import find_dlpack_include_path, find_include_path
|
|
|
|
logger = init_logger(__name__)
|
|
logger.info("Generating .clangd file...")
|
|
include_paths = [find_include_path(), find_dlpack_include_path()] + DEFAULT_INCLUDE
|
|
|
|
# TODO(ROCm): hiprtc JIT cache should be separate from nvcc JIT cache to avoid stale binaries.
|
|
if is_rocm():
|
|
arch_flags = ["-xhip", f"--offload-arch={get_rocm_gfx_arch() or 'gfx1201'}"]
|
|
else:
|
|
try:
|
|
status = subprocess.run(
|
|
args=["nvidia-smi", "--query-gpu=compute_cap", "--format=csv,noheader"],
|
|
capture_output=True,
|
|
check=True,
|
|
)
|
|
compute_cap = status.stdout.decode("utf-8").strip().split("\n")[0]
|
|
major, minor = compute_cap.split(".")
|
|
except (subprocess.CalledProcessError, FileNotFoundError, ValueError):
|
|
import torch
|
|
|
|
major, minor = torch.cuda.get_device_capability()
|
|
arch_flags = ["-xcuda", f"--cuda-gpu-arch=sm_{major}{minor}"]
|
|
compile_flags = ",\n ".join(
|
|
arch_flags + ["-std=c++20", "-Wall", "-Wextra"]
|
|
+ [f"-isystem{path}" for path in include_paths]
|
|
)
|
|
clangd_content = f"""
|
|
CompileFlags:
|
|
Add: [
|
|
{compile_flags}
|
|
]
|
|
"""
|
|
if os.path.exists(".clangd"):
|
|
logger.warning(".clangd file already exists, nothing done.")
|
|
logger.warning(f"suggested content: {clangd_content}")
|
|
else:
|
|
with open(".clangd", "w") as f:
|
|
f.write(clangd_content)
|
|
logger.info(".clangd file generated.")
|
|
|
|
|
|
generate_clangd()
|