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 15, 14:45 UTC
fix: spelling (#16466)
Signed-off-by: Tianer Zhou <ezhoureal@gmail.com>
Tianer Zhou committed
Apr 12, 2025 at 14:24 UTC
4a3a5187225d12ac63cf4422925423a69d1b6008
1 file changed
+1
-1
csrc/custom_all_reduce.cuh
+1
-1
@@ -375,7 +375,7 @@ class CustomAllreduce {
375
bool fully_connected_;
376
377
RankSignals sg_;
378
- // Stores an map from a pointer to its peer pointers from all ranks.
378
+ // Stores a map from a pointer to its peer pointers from all ranks.
379
std::unordered_map<void*, RankData*> buffers_;
380
Signal* self_sg_;
381