Index

_

_impl_map (vortex_torch.cache.elementwise.Elementwise attribute) (vortex_torch.cache.elementwise_binary.Elementwise_Binary attribute) (vortex_torch.cache.fill.Fill attribute) (vortex_torch.cache.matmul.GeMM attribute) (vortex_torch.cache.reduce.Reduce attribute) (vortex_torch.indexer.elementwise.Elementwise attribute) (vortex_torch.indexer.elementwise_binary.Elementwise_Binary attribute) (vortex_torch.indexer.matmul.GeMM attribute) (vortex_torch.indexer.matmul.GeMV attribute) (vortex_torch.indexer.output_func.topK attribute) (vortex_torch.indexer.reduce.Reduce attribute) (vortex_torch.indexer.save_load.Load attribute) (vortex_torch.indexer.save_load.Save attribute) (vortex_torch.indexer.scan.Normalize attribute) (vortex_torch.indexer.scan.Softmax attribute) (vortex_torch.indexer.transpose.Transpose attribute)

A

Abs (class in vortex_torch.cache.elementwise) (class in vortex_torch.indexer.elementwise) (vortex_torch.utils.ElementwiseOpType attribute) Add (class in vortex_torch.cache.elementwise_binary) (class in vortex_torch.indexer.elementwise_binary) (vortex_torch.utils.ElementwiseBinaryOpType attribute) add_aux_flops() (vortex_torch.abs.context_base.ContextBase method) (vortex_torch.abs.ContextBase method) add_aux_memory() (vortex_torch.abs.context_base.ContextBase method) (vortex_torch.abs.ContextBase method) Add_Mul (class in vortex_torch.cache.elementwise) (class in vortex_torch.indexer.elementwise) (vortex_torch.utils.ElementwiseOpType attribute)

alpha (vortex_torch.cache.elementwise.Elementwise attribute) (vortex_torch.cache.elementwise_binary.Elementwise_Binary attribute) (vortex_torch.cache.fill.Fill attribute) (vortex_torch.indexer.elementwise.Elementwise attribute) (vortex_torch.indexer.elementwise_binary.Elementwise_Binary attribute) as_vtensor() (in module vortex_torch.abs) (in module vortex_torch.abs.tensor) assert_created() (vortex_torch.abs.context_base.ContextBase method) (vortex_torch.abs.ContextBase method)

B

batch_size (vortex_torch.indexer.context.Context attribute) BATCHED (vortex_torch.abs.FORMAT attribute), [1] (vortex_torch.abs.tensor.FORMAT attribute), [1] beta (vortex_torch.cache.elementwise.Elementwise attribute) (vortex_torch.cache.elementwise_binary.Elementwise_Binary attribute) (vortex_torch.indexer.elementwise.Elementwise attribute) (vortex_torch.indexer.elementwise_binary.Elementwise_Binary attribute)

BlockSparseAttention (class in vortex_torch.flow.algorithms) build_vflow() (in module vortex_torch.flow.loader)

C

chunkwise_hn2nh_transpose() (in module vortex_torch.indexer.utils_sglang) chunkwise_hn2nh_transpose_fa3() (in module vortex_torch.indexer.utils_sglang) chunkwise_nh2hn_transpose() (in module vortex_torch.indexer.utils_sglang) clear_aux_flops() (vortex_torch.abs.context_base.ContextBase method) (vortex_torch.abs.ContextBase method) clear_aux_memory() (vortex_torch.abs.context_base.ContextBase method) (vortex_torch.abs.ContextBase method) Context (class in vortex_torch.cache.context) (class in vortex_torch.indexer.context) ContextBase (class in vortex_torch.abs) (class in vortex_torch.abs.context_base)

create() (vortex_torch.abs.context_base.ContextBase method) (vortex_torch.abs.ContextBase method) (vortex_torch.cache.context.Context method) (vortex_torch.indexer.context.Context method) create_cache() (vortex_torch.flow.algorithms.BlockSparseAttention method) (vortex_torch.flow.algorithms.GQABlockSparseAttention method) (vortex_torch.flow.algorithms.GQAQuestSparseAttention method) (vortex_torch.flow.flow.vFlow method) created (vortex_torch.abs.context_base.ContextBase property) (vortex_torch.abs.ContextBase property)

D

dense_kv_indices (vortex_torch.indexer.context.Context attribute) dense_kv_indptr (vortex_torch.indexer.context.Context attribute) dim (vortex_torch.cache.reduce.Reduce attribute) (vortex_torch.indexer.reduce.Reduce attribute) (vortex_torch.indexer.scan.Normalize attribute) (vortex_torch.indexer.scan.Softmax attribute)

E

Elementwise (class in vortex_torch.cache.elementwise) (class in vortex_torch.indexer.elementwise) Elementwise_Binary (class in vortex_torch.cache.elementwise_binary) (class in vortex_torch.indexer.elementwise_binary) ElementwiseBinaryOpType (class in vortex_torch.utils) ElementwiseOpType (class in vortex_torch.utils) execute (vortex_torch.utils.Mode attribute) execute() (vortex_torch.abs.context_base.ContextBase method) (vortex_torch.abs.ContextBase method) (vortex_torch.abs.op.vOp method) (vortex_torch.abs.vOp method) (vortex_torch.cache.elementwise.Elementwise method) (vortex_torch.cache.elementwise_binary.Elementwise_Binary method) (vortex_torch.cache.fill.Fill method) (vortex_torch.cache.matmul.GeMM method) (vortex_torch.cache.reduce.Reduce method) (vortex_torch.indexer.elementwise.Elementwise method) (vortex_torch.indexer.elementwise_binary.Elementwise_Binary method) (vortex_torch.indexer.matmul.GeMM method) (vortex_torch.indexer.matmul.GeMV method) (vortex_torch.indexer.output_func.topK method) (vortex_torch.indexer.reduce.Reduce method) (vortex_torch.indexer.save_load.Load method) (vortex_torch.indexer.save_load.Save method) (vortex_torch.indexer.scan.Normalize method) (vortex_torch.indexer.scan.Softmax method) (vortex_torch.indexer.transpose.Transpose method)

F

Fill (class in vortex_torch.cache.fill) FlowInitError FlowLoadError FORMAT (class in vortex_torch.abs) (class in vortex_torch.abs.tensor) forward_cache() (vortex_torch.flow.algorithms.BlockSparseAttention method) (vortex_torch.flow.algorithms.GQABlockSparseAttention method) (vortex_torch.flow.algorithms.GQAQuestSparseAttention method) (vortex_torch.flow.flow.vFlow method)

forward_indexer() (vortex_torch.flow.algorithms.BlockSparseAttention method) (vortex_torch.flow.algorithms.GQABlockSparseAttention method) (vortex_torch.flow.algorithms.GQAQuestSparseAttention method) (vortex_torch.flow.flow.vFlow method)

G

GeMM (class in vortex_torch.cache.matmul) (class in vortex_torch.indexer.matmul) GeMV (class in vortex_torch.indexer.matmul) get() (in module vortex_torch.flow.registry) get_cache_meta_info() (vortex_torch.flow.flow.vFlow method)

get_ctx() (in module vortex_torch.indexer.context) get_token_ratio() (vortex_torch.flow.flow.vFlow method) GQABlockSparseAttention (class in vortex_torch.flow.algorithms) GQAQuestSparseAttention (class in vortex_torch.flow.algorithms) group_size (vortex_torch.indexer.context.Context attribute)

H

has() (in module vortex_torch.flow.registry) head_dim (vortex_torch.cache.context.Context attribute) (vortex_torch.indexer.context.Context attribute)

head_num (vortex_torch.cache.context.Context attribute)

I

impl (vortex_torch.cache.elementwise.Elementwise attribute) (vortex_torch.cache.elementwise_binary.Elementwise_Binary attribute) (vortex_torch.cache.fill.Fill attribute) (vortex_torch.cache.matmul.GeMM attribute) (vortex_torch.cache.reduce.Reduce attribute) (vortex_torch.indexer.elementwise.Elementwise attribute) (vortex_torch.indexer.elementwise_binary.Elementwise_Binary attribute) (vortex_torch.indexer.matmul.GeMM attribute) (vortex_torch.indexer.matmul.GeMV attribute) (vortex_torch.indexer.output_func.topK attribute) (vortex_torch.indexer.reduce.Reduce attribute) (vortex_torch.indexer.save_load.Load attribute) (vortex_torch.indexer.save_load.Save attribute) (vortex_torch.indexer.scan.Normalize attribute) (vortex_torch.indexer.scan.Softmax attribute) (vortex_torch.indexer.transpose.Transpose attribute)

indexer_dtype (vortex_torch.indexer.context.Context attribute) indices_to_page_table() (in module vortex_torch.indexer.utils_sglang)

K

kv_last_page_len (vortex_torch.indexer.context.Context attribute)

L

L2Norm (class in vortex_torch.cache.reduce) (class in vortex_torch.indexer.reduce) (vortex_torch.utils.ReduceType attribute)

list_keys() (in module vortex_torch.flow.registry) Load (class in vortex_torch.indexer.save_load)

M

Max (class in vortex_torch.cache.reduce) (class in vortex_torch.indexer.reduce) (vortex_torch.utils.ReduceType attribute) max_chunk_size (vortex_torch.indexer.context.Context attribute) max_new_tokens_per_batch (vortex_torch.cache.context.Context attribute) max_num_pages (vortex_torch.indexer.context.Context attribute) max_num_pages_per_request (vortex_torch.indexer.context.Context attribute) max_num_workloads (vortex_torch.indexer.context.Context attribute) Maximum (class in vortex_torch.cache.elementwise_binary) (class in vortex_torch.indexer.elementwise_binary) (vortex_torch.utils.ElementwiseBinaryOpType attribute) Mean (class in vortex_torch.cache.reduce) (class in vortex_torch.indexer.reduce) (vortex_torch.utils.ReduceType attribute) Min (class in vortex_torch.cache.reduce) (class in vortex_torch.indexer.reduce) (vortex_torch.utils.ReduceType attribute) min_chunk_size (vortex_torch.indexer.context.Context attribute) Minimum (class in vortex_torch.cache.elementwise_binary) (class in vortex_torch.indexer.elementwise_binary) (vortex_torch.utils.ElementwiseBinaryOpType attribute) missing() (vortex_torch.abs.context_base.ContextBase method) (vortex_torch.abs.ContextBase method) Mode (class in vortex_torch.utils) mode (vortex_torch.abs.context_base.ContextBase attribute) (vortex_torch.abs.ContextBase attribute) (vortex_torch.cache.context.Context attribute) (vortex_torch.indexer.context.Context attribute) module vortex_torch vortex_torch.abs vortex_torch.abs.context_base vortex_torch.abs.op vortex_torch.abs.tensor vortex_torch.cache vortex_torch.cache.context vortex_torch.cache.elementwise vortex_torch.cache.elementwise_binary vortex_torch.cache.fill vortex_torch.cache.matmul vortex_torch.cache.reduce vortex_torch.cache.triton_kernels vortex_torch.cache.triton_kernels.elementwise_binary_impl vortex_torch.cache.triton_kernels.elementwise_impl vortex_torch.cache.triton_kernels.fill_impl vortex_torch.cache.triton_kernels.matmul_impl vortex_torch.cache.triton_kernels.reduce_impl vortex_torch.cache.triton_kernels.set_kv vortex_torch.flow vortex_torch.flow.algorithms vortex_torch.flow.flow vortex_torch.flow.loader vortex_torch.flow.registry vortex_torch.indexer vortex_torch.indexer.context vortex_torch.indexer.elementwise vortex_torch.indexer.elementwise_binary vortex_torch.indexer.matmul vortex_torch.indexer.output_func vortex_torch.indexer.reduce vortex_torch.indexer.save_load vortex_torch.indexer.scan vortex_torch.indexer.transpose vortex_torch.indexer.triton_kernels vortex_torch.indexer.triton_kernels.elementwise_binary_impl vortex_torch.indexer.triton_kernels.elementwise_impl vortex_torch.indexer.triton_kernels.matmul_impl vortex_torch.indexer.triton_kernels.mv_impl vortex_torch.indexer.triton_kernels.normalize_impl vortex_torch.indexer.triton_kernels.reduce_impl vortex_torch.indexer.triton_kernels.save_load_impl vortex_torch.indexer.triton_kernels.softmax_impl vortex_torch.indexer.triton_kernels.transpose_impl vortex_torch.indexer.triton_kernels.utils_impl vortex_torch.indexer.utils_sglang vortex_torch.utils vortex_torch.version

Mul (vortex_torch.utils.ElementwiseBinaryOpType attribute) Multiply (class in vortex_torch.cache.elementwise_binary) (class in vortex_torch.indexer.elementwise_binary)

N

name (vortex_torch.abs.context_base.ContextBase attribute) (vortex_torch.abs.ContextBase attribute) (vortex_torch.cache.context.Context attribute) (vortex_torch.indexer.context.Context attribute)

Normalize (class in vortex_torch.indexer.scan) num_kv_heads (vortex_torch.indexer.context.Context attribute) num_qo_heads (vortex_torch.indexer.context.Context attribute) num_sms (vortex_torch.indexer.context.Context attribute)

O

op_type (vortex_torch.cache.elementwise.Elementwise attribute) (vortex_torch.cache.elementwise_binary.Elementwise_Binary attribute) (vortex_torch.indexer.elementwise.Elementwise attribute) (vortex_torch.indexer.elementwise_binary.Elementwise_Binary attribute) output_buffer (vortex_torch.cache.elementwise.Elementwise attribute) (vortex_torch.cache.elementwise_binary.Elementwise_Binary attribute) (vortex_torch.cache.matmul.GeMM attribute) (vortex_torch.cache.reduce.Reduce attribute) (vortex_torch.indexer.elementwise.Elementwise attribute) (vortex_torch.indexer.elementwise_binary.Elementwise_Binary attribute) (vortex_torch.indexer.matmul.GeMM attribute) (vortex_torch.indexer.matmul.GeMV attribute) (vortex_torch.indexer.reduce.Reduce attribute) (vortex_torch.indexer.save_load.Load attribute) (vortex_torch.indexer.transpose.Transpose attribute)

output_format (vortex_torch.cache.elementwise.Elementwise attribute) (vortex_torch.cache.elementwise_binary.Elementwise_Binary attribute) (vortex_torch.cache.matmul.GeMM attribute) (vortex_torch.cache.reduce.Reduce attribute) (vortex_torch.indexer.elementwise.Elementwise attribute) (vortex_torch.indexer.elementwise_binary.Elementwise_Binary attribute) (vortex_torch.indexer.matmul.GeMM attribute) (vortex_torch.indexer.matmul.GeMV attribute) (vortex_torch.indexer.reduce.Reduce attribute) (vortex_torch.indexer.save_load.Load attribute) (vortex_torch.indexer.save_load.Save attribute) (vortex_torch.indexer.scan.Normalize attribute) (vortex_torch.indexer.scan.Softmax attribute) (vortex_torch.indexer.transpose.Transpose attribute)

P

page_reserved_bos (vortex_torch.indexer.context.Context attribute) page_reserved_eos (vortex_torch.indexer.context.Context attribute) page_size (vortex_torch.cache.context.Context attribute) (vortex_torch.indexer.context.Context attribute) PAGED (vortex_torch.abs.FORMAT attribute), [1] (vortex_torch.abs.tensor.FORMAT attribute), [1] plan_decode() (in module vortex_torch.indexer.utils_sglang) plan_decode_fa3() (in module vortex_torch.indexer.utils_sglang) plan_prefill() (in module vortex_torch.indexer.utils_sglang) plan_prefill_fa3() (in module vortex_torch.indexer.utils_sglang) profile (vortex_torch.utils.Mode attribute) profile() (vortex_torch.abs.context_base.ContextBase method) (vortex_torch.abs.ContextBase method) (vortex_torch.abs.op.vOp method) (vortex_torch.abs.vOp method) (vortex_torch.cache.elementwise.Elementwise method) (vortex_torch.cache.elementwise_binary.Elementwise_Binary method) (vortex_torch.cache.fill.Fill method) (vortex_torch.cache.matmul.GeMM method) (vortex_torch.cache.reduce.Reduce method) (vortex_torch.indexer.elementwise.Elementwise method) (vortex_torch.indexer.elementwise_binary.Elementwise_Binary method) (vortex_torch.indexer.matmul.GeMM method) (vortex_torch.indexer.matmul.GeMV method) (vortex_torch.indexer.output_func.topK method) (vortex_torch.indexer.reduce.Reduce method) (vortex_torch.indexer.save_load.Load method) (vortex_torch.indexer.save_load.Save method) (vortex_torch.indexer.scan.Normalize method) (vortex_torch.indexer.scan.Softmax method) (vortex_torch.indexer.transpose.Transpose method)

R

RAGGED (vortex_torch.abs.FORMAT attribute), [1] (vortex_torch.abs.tensor.FORMAT attribute), [1] Reduce (class in vortex_torch.cache.reduce) (class in vortex_torch.indexer.reduce) reduce_type (vortex_torch.cache.reduce.Reduce attribute) (vortex_torch.indexer.reduce.Reduce attribute)

ReduceType (class in vortex_torch.utils) register() (in module vortex_torch.flow.registry) RegistryError Relu (class in vortex_torch.cache.elementwise) (class in vortex_torch.indexer.elementwise) (vortex_torch.utils.ElementwiseOpType attribute) run_indexer_virtual() (vortex_torch.flow.flow.vFlow method)

S

Save (class in vortex_torch.indexer.save_load) scale (vortex_torch.indexer.scan.Softmax attribute) set_batch_size() (vortex_torch.indexer.context.Context method) Sigmoid (class in vortex_torch.cache.elementwise) (class in vortex_torch.indexer.elementwise) (vortex_torch.utils.ElementwiseOpType attribute) Silu (class in vortex_torch.cache.elementwise) (class in vortex_torch.indexer.elementwise) (vortex_torch.utils.ElementwiseOpType attribute)

Softmax (class in vortex_torch.indexer.scan) sparse_kv_indices (vortex_torch.indexer.context.Context attribute) sparse_kv_indptr (vortex_torch.indexer.context.Context attribute) Sum (class in vortex_torch.indexer.reduce) (vortex_torch.utils.ReduceType attribute) summary() (vortex_torch.abs.context_base.ContextBase method) (vortex_torch.abs.ContextBase method)

T

topK (class in vortex_torch.indexer.output_func) topk_val (vortex_torch.indexer.context.Context attribute)

total_num_pages (vortex_torch.cache.context.Context attribute) Transpose (class in vortex_torch.indexer.transpose)

V

vFlow (class in vortex_torch.flow.flow) vOp (class in vortex_torch.abs) (class in vortex_torch.abs.op) vortex_torch module vortex_torch.abs module vortex_torch.abs.context_base module vortex_torch.abs.op module vortex_torch.abs.tensor module vortex_torch.cache module vortex_torch.cache.context module vortex_torch.cache.elementwise module vortex_torch.cache.elementwise_binary module vortex_torch.cache.fill module vortex_torch.cache.matmul module vortex_torch.cache.reduce module vortex_torch.cache.triton_kernels module vortex_torch.cache.triton_kernels.elementwise_binary_impl module vortex_torch.cache.triton_kernels.elementwise_impl module vortex_torch.cache.triton_kernels.fill_impl module vortex_torch.cache.triton_kernels.matmul_impl module vortex_torch.cache.triton_kernels.reduce_impl module vortex_torch.cache.triton_kernels.set_kv module vortex_torch.flow module vortex_torch.flow.algorithms module vortex_torch.flow.flow module vortex_torch.flow.loader module vortex_torch.flow.registry module

vortex_torch.indexer module vortex_torch.indexer.context module vortex_torch.indexer.elementwise module vortex_torch.indexer.elementwise_binary module vortex_torch.indexer.matmul module vortex_torch.indexer.output_func module vortex_torch.indexer.reduce module vortex_torch.indexer.save_load module vortex_torch.indexer.scan module vortex_torch.indexer.transpose module vortex_torch.indexer.triton_kernels module vortex_torch.indexer.triton_kernels.elementwise_binary_impl module vortex_torch.indexer.triton_kernels.elementwise_impl module vortex_torch.indexer.triton_kernels.matmul_impl module vortex_torch.indexer.triton_kernels.mv_impl module vortex_torch.indexer.triton_kernels.normalize_impl module vortex_torch.indexer.triton_kernels.reduce_impl module vortex_torch.indexer.triton_kernels.save_load_impl module vortex_torch.indexer.triton_kernels.softmax_impl module vortex_torch.indexer.triton_kernels.transpose_impl module vortex_torch.indexer.triton_kernels.utils_impl module vortex_torch.indexer.utils_sglang module vortex_torch.utils module vortex_torch.version module vTensor (class in vortex_torch.abs) (class in vortex_torch.abs.tensor)

W

winfo_chunk_size (vortex_torch.indexer.context.Context attribute) winfo_kv_lens (vortex_torch.indexer.context.Context attribute)

winfo_kv_offsets (vortex_torch.indexer.context.Context attribute) winfo_num_workloads (vortex_torch.indexer.context.Context attribute) winfo_q_indices (vortex_torch.indexer.context.Context attribute)