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

[Bugfix][ROCm][Build] Fix build regression on ROCm (#21393)

Browse Source 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
This commit is contained in:
Gregory Shtrasberg
2025-07-22 23:27:41 -04:00
committed by GitHub
parent c401c64b4c
commit 3ec7170ff1
3 changed files with 16 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
csrc/torch_bindings.cpp
View File

@@ -601,15 +601,6 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
ops.impl("dynamic_scaled_int8_quant", torch::kCUDA,
&dynamic_scaled_int8_quant);
// Compute per-token-group FP8 quantized tensor and scaling factor.
ops.def(
"per_token_group_fp8_quant(Tensor input, Tensor! output_q, Tensor! "
"output_s, "
"int group_size, float eps, float fp8_min, float fp8_max, bool "
"scale_ue8m0) -> ()");
ops.impl("per_token_group_fp8_quant", torch::kCUDA,
&per_token_group_quant_fp8);
// Mamba selective scan kernel
ops.def(
"selective_scan_fwd(Tensor! u, Tensor! delta,"
@@ -624,6 +615,15 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
ops.impl("selective_scan_fwd", torch::kCUDA, &selective_scan_fwd);
#ifndef USE_ROCM
// Compute per-token-group FP8 quantized tensor and scaling factor.
ops.def(
"per_token_group_fp8_quant(Tensor input, Tensor! output_q, Tensor! "
"output_s, "
"int group_size, float eps, float fp8_min, float fp8_max, bool "
"scale_ue8m0) -> ()");
ops.impl("per_token_group_fp8_quant", torch::kCUDA,
&per_token_group_quant_fp8);
// reorder weight for AllSpark Ampere W8A16 Fused Gemm kernel
ops.def(
"rearrange_kn_weight_as_n32k16_order(Tensor b_qweight, Tensor b_scales, "