EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

fix link in README (#3153)

Browse Source
This commit is contained in:
Yineng Zhang
2025-01-26 21:30:00 +08:00
committed by GitHub
parent 1dda8c5e4c
commit 02431b9ad2
2 changed files with 1 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
sgl-kernel/developer_guide.md
View File

@@ -26,7 +26,7 @@ Third-party libraries:
Steps to add a new kernel:
1. Implement in [src/sgl-kernel/csrc/](https://github.com/sgl-project/sglang/tree/main/sgl-kernel/src/sgl-kernel/csrc)
2. Expose interface in [src/sgl-kernel/include/sgl_kernel_ops.h](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/src/sgl-kernel/include/sgl_kernel_ops.h)
2. Expose interface in [src/sgl-kernel/include/sgl_kernels_ops.h](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/src/sgl-kernel/include/sgl_kernels_ops.h)
3. Create torch extension in [src/sgl-kernel/torch_extension.cc](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/src/sgl-kernel/torch_extension.cc)
4. Create Python wrapper in [src/sgl-kernel/ops/\_\_init\_\_.py](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/src/sgl-kernel/ops/__init__.py)
5. Expose Python interface in [src/sgl-kernel/\_\_init\_\_.py](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/src/sgl-kernel/__init__.py)

3
sgl-kernel/setup.py
View File

@@ -88,7 +88,6 @@ sources = [
"src/sgl-kernel/csrc/rotary_embedding.cu",
"3rdparty/flashinfer/csrc/activation.cu",
"3rdparty/flashinfer/csrc/bmm_fp8.cu",
"3rdparty/flashinfer/csrc/group_gemm.cu",
"3rdparty/flashinfer/csrc/norm.cu",
"3rdparty/flashinfer/csrc/sampling.cu",
"3rdparty/flashinfer/csrc/renorm.cu",
@@ -103,7 +102,6 @@ sm_version = _get_device_sm()
if torch.cuda.is_available():
if cuda_version >= (12, 0) and sm_version >= 90:
nvcc_flags.append("-gencode=arch=compute_90a,code=sm_90a")
sources.append("3rdparty/flashinfer/csrc/group_gemm_sm90.cu")
if sm_version >= 90:
nvcc_flags.extend(nvcc_flags_fp8)
if sm_version >= 80:
@@ -112,7 +110,6 @@ else:
# compilation environment without GPU
if enable_sm90a:
nvcc_flags.append("-gencode=arch=compute_90a,code=sm_90a")
sources.append("3rdparty/flashinfer/csrc/group_gemm_sm90.cu")
if enable_fp8:
nvcc_flags.extend(nvcc_flags_fp8)
if enable_bf16: