A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 23:45 UTC
[AMD][CI/Build] Fix the AMD issue caused by inappropriate of symbol exposure (#21647)
Signed-off-by: Lu Fang <lufang@fb.com>
Lu Fang committed
Jul 28, 2025 at 13:11 UTC
9ba1c88a939fd4f481e2e0aed7cc29ff1258ac7e
1 file changed
+2
-2
CMakeLists.txt
+2
-2
@@ -243,7 +243,6 @@ set(VLLM_EXT_SRC
243
"csrc/sampler.cu"
244
"csrc/cuda_view.cu"
245
"csrc/quantization/gptq/q_gemm.cu"
246
- "csrc/quantization/compressed_tensors/int8_quant_kernels.cu"
246
"csrc/quantization/fp8/common.cu"
247
"csrc/quantization/fused_kernels/fused_layernorm_dynamic_per_token_quant.cu"
248
"csrc/quantization/gguf/gguf_kernel.cu"
@@ -297,7 +296,8 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
296
"csrc/sparse/cutlass/sparse_scaled_mm_entry.cu"
297
"csrc/cutlass_extensions/common.cpp"
298
"csrc/attention/mla/cutlass_mla_entry.cu"
300
- "csrc/quantization/fp8/per_token_group_quant.cu")
299
+ "csrc/quantization/fp8/per_token_group_quant.cu"
300
+ "csrc/quantization/compressed_tensors/int8_quant_kernels.cu")
301
302
set_gencode_flags_for_srcs(
303
SRCS "${VLLM_EXT_SRC}"