Commit 719e82c
authored
[TRTLLM-10030][perf] beam search (remove GPU sync + fix batching + refactor) (NVIDIA#11276)
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>1 parent e483c72 commit 719e82c
File tree
5 files changed
+253
-248
lines changed- tensorrt_llm/_torch/pyexecutor
- tests/unittest/_torch/sampler
5 files changed
+253
-248
lines changed
0 commit comments