[Bugfix][ROCm][Build] Fix build regression on ROCm (#21393)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
This commit is contained in:
+5
-5
@@ -287,6 +287,11 @@ void scaled_fp4_experts_quant(
|
||||
torch::Tensor const& input, torch::Tensor const& input_global_scale,
|
||||
torch::Tensor const& input_offset_by_experts,
|
||||
torch::Tensor const& output_scale_offset_by_experts);
|
||||
|
||||
void per_token_group_quant_fp8(const torch::Tensor& input,
|
||||
torch::Tensor& output_q, torch::Tensor& output_s,
|
||||
int64_t group_size, double eps, double fp8_min,
|
||||
double fp8_max, bool scale_ue8m0);
|
||||
#endif
|
||||
|
||||
void static_scaled_int8_quant(torch::Tensor& out, torch::Tensor const& input,
|
||||
@@ -297,11 +302,6 @@ void dynamic_scaled_int8_quant(torch::Tensor& out, torch::Tensor const& input,
|
||||
torch::Tensor& scales,
|
||||
std::optional<torch::Tensor> const& azp);
|
||||
|
||||
void per_token_group_quant_fp8(const torch::Tensor& input,
|
||||
torch::Tensor& output_q, torch::Tensor& output_s,
|
||||
int64_t group_size, double eps, double fp8_min,
|
||||
double fp8_max, bool scale_ue8m0);
|
||||
|
||||
torch::Tensor gptq_gemm(torch::Tensor a, torch::Tensor b_q_weight,
|
||||
torch::Tensor b_gptq_qzeros,
|
||||
torch::Tensor b_gptq_scales, torch::Tensor b_g_idx,
|
||||
|
||||
Reference in New Issue
Block a user