Merge tag 'v0.8.3' into v0.8.3-dev

csrc/rocm/ops.h

@@ -7,8 +7,9 @@ void paged_attention(torch::Tensor& out, torch::Tensor& exp_sums,
                      torch::Tensor& query, torch::Tensor& key_cache,
                      torch::Tensor& value_cache, int64_t num_kv_heads,
                      double scale, torch::Tensor& block_tables,
-                     torch::Tensor& context_lens, int64_t block_size,
-                     int64_t max_context_len,
+                     torch::Tensor& context_lens,
+                     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);