biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[ROCm][GPTQ][Bugfix] Fix GPTQ GEMM kernel output zeroing race condition (#30719)

Browse Source 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
Andreas Karatzas
2025-12-29 03:13:14 -06:00
committed by GitHub
parent 45c1ca1ca1
commit 3ecfdc3776
1 changed files with 1 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
csrc/quantization/gptq/q_gemm.cu
View File

@@ -233,11 +233,6 @@ __global__ void gemm_half_q_half_gptq_4bit_kernel(
// Zero output
if (n >= size_n) return;
if (blockIdx.z == 0) {
for (int m = 0; m < m_count; m++)
*((uint64_t*)c_.item_ptr(offset_m + m, n)) = 0;
}
__syncthreads();
// Find initial group
@@ -372,11 +367,6 @@ __global__ void gemm_half_q_half_gptq_2bit_kernel(
// Zero output
if (n >= size_n) return;
if (blockIdx.z == 0) {
for (int m = 0; m < m_count; m++)
*((uint64_t*)c_.item_ptr(offset_m + m, n)) = 0;
}
__syncthreads();
// Find initial group
@@ -494,11 +484,6 @@ __global__ void gemm_half_q_half_gptq_3bit_kernel(
// Zero output
if (n >= size_n) return;
if (blockIdx.z == 0) {
for (int m = 0; m < m_count; m++)
*((uint64_t*)c_.item_ptr(offset_m + m, n)) = 0;
}
__syncthreads();
// Find initial group
@@ -623,11 +608,6 @@ __global__ void gemm_half_q_half_gptq_8bit_kernel(
// Zero output
if (n >= size_n) return;
if (blockIdx.z == 0) {
for (int m = 0; m < m_count; m++)
*((uint64_t*)c_.item_ptr(offset_m + m, n)) = 0;
}
__syncthreads();
// Find initial group
@@ -1224,9 +1204,6 @@ __global__ void gemm_half_q_half_alt_4bit_kernel(
__halves2half2(__int2half_rn(val & 0xF), __int2half_rn(val >> 4));
}
if (blockIdx.z == 0) {
for (int m = 0; m < b_end; m++) mul[(b + m) * width + w] = __int2half_rn(0);
}
__syncthreads();
int i = width * h + w;
@@ -1319,9 +1296,6 @@ __global__ void gemm_half_q_half_alt_8bit_kernel(
}
}
if (blockIdx.z == 0) {
for (int m = 0; m < b_end; m++) mul[(b + m) * width + w] = __int2half_rn(0);
}
__syncthreads();
int i = width * h + w;
@@ -1857,7 +1831,7 @@ torch::Tensor gptq_gemm(torch::Tensor a, torch::Tensor b_q_weight,
bool use_exllama, bool use_v2_format, int64_t bit) {
const at::cuda::OptionalCUDAGuard device_guard(device_of(a));
auto options = torch::TensorOptions().dtype(a.dtype()).device(a.device());
at::Tensor c = torch::empty({a.size(0), b_q_weight.size(1)}, options);
at::Tensor c = torch::zeros({a.size(0), b_q_weight.size(1)}, options);
at::Tensor temp_dq = torch::empty(
{b_q_weight.size(0) * 32 / bit, b_q_weight.size(1)}, options);