chore: improve comments in README

Author: cenxi.lx

README.md

@@ -70,7 +70,8 @@ dq, dk, dv, db, dg, dh0 = chunk_gated_delta_rule_bwd(
 ## Tests
 
 ```bash
-pip install flash_linear_attention==0.5.0 # require flash linear attention for comparison
+# require flash linear attention for comparison
+pip install flash_linear_attention==0.5.0
 
 cd tests
 python test_gdr.py --set develop
@@ -92,7 +93,8 @@ Specifically, the forward (FWD) benchmarks measure single-kernel latency for dif
 More detail in [./benchmark/benchmark_results_H200.txt].
 
 ```bash
-pip install flash_linear_attention==0.5.0 flashinfer-python==0.6.9 # require flash linear attention and flashinfer for comparison
+# require flash linear attention and flashinfer for comparison
+pip install flash_linear_attention==0.5.0 flashinfer-python==0.6.9
 
 cd benchmark
 python bench_gated_delta_rule.py