Skip to content

[Easy] Eliminate c10::optional usage in vllm/csrc #17819

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 8, 2025
Merged

[Easy] Eliminate c10::optional usage in vllm/csrc #17819

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions csrc/quantization/gptq_allspark/allspark_qgemm_w8a16.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ at::Tensor as_g_workspace;

torch::Tensor allspark_w8a16_gemm(
torch::Tensor const& a, torch::Tensor const& b_qweight,
torch::Tensor const& b_scales, c10::optional<torch::Tensor> const& b_qzeros,
torch::Tensor const& b_scales, std::optional<torch::Tensor> const& b_qzeros,
int64_t n, int64_t group_size, int64_t sm_count, int64_t sm_version,
int64_t CUBLAS_M_THRESHOLD, bool has_zp, bool n32k16_reorder) {
TORCH_CHECK_NOT_IMPLEMENTED(
Expand Down Expand Up @@ -918,7 +918,7 @@ void allspark_qgemm_w8a16_perc_ampere(

torch::Tensor allspark_w8a16_gemm(
torch::Tensor const& a, torch::Tensor const& b_qweight,
torch::Tensor const& b_scales, c10::optional<torch::Tensor> const& b_qzeros,
torch::Tensor const& b_scales, std::optional<torch::Tensor> const& b_qzeros,
int64_t n, int64_t group_size, int64_t sm_count, int64_t sm_version,
int64_t CUBLAS_M_THRESHOLD, bool has_zp, bool n32k16_reorder) {
// Verify device and strides
Expand Down
4 changes: 2 additions & 2 deletions csrc/quantization/gptq_allspark/allspark_repack.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,9 +100,9 @@ void rearrange_kn_weight_as_n32k16_order_ldg16(

void rearrange_kn_weight_as_n32k16_order(
torch::Tensor const& b_qweight, torch::Tensor const& b_scales,
c10::optional<torch::Tensor> const& b_zeros, bool has_zp,
std::optional<torch::Tensor> const& b_zeros, bool has_zp,
torch::Tensor& b_qweight_reorder, torch::Tensor& b_scales_reorder,
c10::optional<torch::Tensor> const& b_zeros_reorder, const int64_t K,
std::optional<torch::Tensor> const& b_zeros_reorder, const int64_t K,
const int64_t N, const int64_t N_32align) {
// Verify device and strides
TORCH_CHECK(b_qweight.device().is_cuda(), "b_qweight is not on GPU");
Expand Down
4 changes: 2 additions & 2 deletions csrc/rocm/attention.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1597,7 +1597,7 @@ void paged_attention_custom_launcher(
torch::Tensor& block_tables, torch::Tensor& context_lens,
const std::optional<torch::Tensor>& query_start_loc, int max_context_len,
const std::optional<torch::Tensor>& alibi_slopes, torch::Tensor& k_scale,
torch::Tensor& v_scale, const c10::optional<torch::Tensor>& fp8_out_scale) {
torch::Tensor& v_scale, const std::optional<torch::Tensor>& fp8_out_scale) {
int num_seqs = block_tables.size(0);
int num_heads = query.size(1);
int head_size = query.size(2);
Expand Down Expand Up @@ -1825,7 +1825,7 @@ void paged_attention(
const std::optional<torch::Tensor>& alibi_slopes,
const std::string& kv_cache_dtype, torch::Tensor& k_scale,
torch::Tensor& v_scale,
const c10::optional<torch::Tensor>& fp8_out_scale) {
const std::optional<torch::Tensor>& fp8_out_scale) {
// clang-format on
const int head_size = query.size(2);
if (kv_cache_dtype == "auto") {
Expand Down
2 changes: 1 addition & 1 deletion csrc/rocm/ops.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,4 +19,4 @@ void paged_attention(
const std::optional<torch::Tensor>& query_start_loc, int64_t block_size,
int64_t max_context_len, const std::optional<torch::Tensor>& alibi_slopes,
const std::string& kv_cache_dtype, torch::Tensor& k_scale,
torch::Tensor& v_scale, const c10::optional<torch::Tensor>& fp8_out_scale);
torch::Tensor& v_scale, const std::optional<torch::Tensor>& fp8_out_scale);