A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 15:45 UTC
[Bugfix] Fixup advance_step.cu warning (#8815)
Tyler Michael Smith committed
Sep 26, 2024 at 19:23 UTC
71d21c73abfb9b12ea402ce6b11c1b8e31eddf4c
1 file changed
+2
-2
csrc/prepare_inputs/advance_step.cu
+2
-2
@@ -211,7 +211,7 @@ void advance_step_flashinfer(
211
printf(" num_seqs = %d\n", num_seqs);
212
printf(" num_queries = %d\n", num_queries);
213
printf(" block_size = %d\n", block_size);
214
- printf(" block_tables.stride(0) = %d\n", block_tables.stride(0));
214
+ printf(" block_tables.stride(0) = %zu\n", block_tables.stride(0));
215
}
216
// Verify all tensors
217
verify_tensor("input_tokens", input_tokens, num_seqs, -1, at::kLong);
@@ -303,4 +303,4 @@ void advance_step_flashinfer(
303
num_seqs, num_queries, block_size, input_tokens, sampled_token_ids,
304
input_positions, seq_lens, slot_mapping, block_tables, paged_kv_indices,
305
paged_kv_indptr, paged_kv_last_page_len, block_table_bound);
306
-}
\ No newline at end of file
306
+}