[Misc] Fused MoE Marlin support for GPTQ (#8217)
This commit is contained in:
@@ -9,4 +9,4 @@ torch::Tensor marlin_gemm_moe(
|
||||
const torch::Tensor& g_idx, const torch::Tensor& perm,
|
||||
torch::Tensor& workspace, int64_t size_m, int64_t size_n, int64_t size_k,
|
||||
bool is_k_full, int64_t num_experts, int64_t topk, int64_t moe_block_size,
|
||||
bool replicate_input, bool apply_weights);
|
||||
bool replicate_input, bool apply_weights);
|
||||
|
||||
Reference in New Issue
Block a user