[Docs] Split slash-combined docstring parameters (#57141)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

vllm/_custom_ops.py

@@ -1482,8 +1482,14 @@ def cutlass_w4a8_moe_mm(
             Cumulative token offsets
         problem_sizes:
             Per-expert (M, N, K) GEMM sizes used by the grouped GEMM launcher.
-        a/b/c/group_scale_strides:
-            Strides describing the memory layout of the input tensors.
+        a_strides:
+            Strides describing the memory layout of a_tensors.
+        b_strides:
+            Strides describing the memory layout of b_tensors.
+        c_strides:
+            Strides describing the memory layout of out_tensors.
+        group_scale_strides:
+            Strides describing the memory layout of b_group_scales.
         maybe_schedule:
             Optional override to choose a specific kernel or epilogue schedule.
 

vllm/model_executor/kernels/attention/dsa/sparse_mqa_logits.py

@@ -190,9 +190,11 @@ def candidate_blocks_to_sparse_indices(
         candidate_blocks: [rows, K] int32 request-local candidate block ids
             (-1 padded), in units of ``candidate_block_size`` positions. K
             must be a power of two (the in-kernel sort); rows may be strided.
-        row_ks/row_ke: [rows] int32 per-row K range; bounds are in the same
+        row_ks: [rows] int32 per-row K range start; bounds are in the same
             (packed-workspace) coordinates the sparse kernel iterates over.
             Pass zeros for the paged path, whose blocks are context-relative.
+        row_ke: [rows] int32 per-row K range end, in the same coordinates as
+            ``row_ks``.
         candidate_block_size: Positions per candidate block.
         sparse_block_kv: Positions per sparse block (8 or 16).
         out: Optional ``(sparse_indices, end)`` buffers to write into,
@@ -322,12 +324,16 @@ def sparse_mqa_logits_prefill_chunk(
         k_scale: [total_kv] int32 packed UE8M0 K scales.
         weights: [rows, H] bf16 per-head weights; the sparse kernels take
             bf16 and do not fold the Q scale in.
-        cu_seqlen_ks/cu_seqlen_ke: [rows] int32 per-token K bounds in the
-            packed workspace.
+        cu_seqlen_ks: [rows] int32 per-token K start bounds in the packed
+            workspace.
+        cu_seqlen_ke: [rows] int32 per-token K end bounds in the packed
+            workspace.
         candidate_blocks: [rows, K] int32 request-local candidate block ids.
         topk_indices: [rows, topk_tokens] output buffer.
-        sparse_indices/end/col_indices: Caller-owned scratch, see
-            `candidate_blocks_to_sparse_indices` and `sparse_topk_remap`.
+        sparse_indices: Caller-owned scratch, see
+            `candidate_blocks_to_sparse_indices`.
+        end: Caller-owned scratch, see `candidate_blocks_to_sparse_indices`.
+        col_indices: Caller-owned scratch, see `sparse_topk_remap`.
         kernel_metadata: DeepGEMM schedule from a previous call with the same
             candidates and bounds (i.e. another indexer layer in the same
             step). When given, the candidate expansion is skipped and
@@ -413,7 +419,9 @@ def sparse_mqa_logits_paged_decode(
         candidate_blocks: [rows, K] int32 candidate block ids.
         topk_indices: [rows, topk_tokens] output buffer.
         row_ks: [rows] int32 zeros (paged blocks are context-relative).
-        sparse_indices/end/col_indices: Caller-owned scratch.
+        sparse_indices: Caller-owned scratch.
+        end: Caller-owned scratch.
+        col_indices: Caller-owned scratch.
         kernel_metadata: See `sparse_mqa_logits_prefill_chunk`.
 
     Returns:

vllm/utils/deep_gemm.py

@@ -726,8 +726,10 @@ def get_sparse_mqa_logits_metadata(
     need a host-side sync to pick one.
 
     Args:
-        cu_seqlen_ks/cu_seqlen_ke: Per-row K range bounds in the packed KV
+        cu_seqlen_ks: Per-row K range start bounds in the packed KV
             workspace, shape [num_q_tokens], dtype int32.
+        cu_seqlen_ke: Per-row K range end bounds in the packed KV workspace,
+            shape [num_q_tokens], dtype int32.
         num_kv_tokens: Total KV tokens in the packed workspace.
         sparse_kv_block_indices: Per-row candidate block ids, shape
             [num_q_tokens, num_max_sparse_blocks], dtype int32. Each row's