Skip to content

[fix] Fixes KV Cache overrides in trtllm-bench #6103

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jul 17, 2025
Merged

[fix] Fixes KV Cache overrides in trtllm-bench #6103

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
70b4dac
Fixes overrides for bench settings.
FrankD412 Jul 16, 2025
a3353e9
Merge branch 'main' into fdinatale/trtllm-bench/kv_cache_cfg_fix
FrankD412 Jul 16, 2025
986064b
Merge branch 'main' into fdinatale/trtllm-bench/kv_cache_cfg_fix
FrankD412 Jul 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions tensorrt_llm/bench/dataclasses/configuration.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,8 +58,6 @@ def get_llm_args(self) -> Dict:
self.world_config.cluster_size,
"trust_remote_code":
True,
"kv_cache_config":
self.settings_config.get_kvcache_config(),
"enable_chunked_prefill":
self.settings_config.chunking,
"extended_runtime_perf_knob_config":
Expand All @@ -82,6 +80,10 @@ def get_llm_args(self) -> Dict:
if self.backend in backend_config_map:
llm_args.update(backend_config_map[self.backend]())

kv_cache_config = self.settings_config.get_kvcache_config().__dict__
backend_cache_config = llm_args.pop("kv_cache_config", {})
llm_args["kv_cache_config"] = backend_cache_config | kv_cache_config

return update_llm_args_with_extra_options(llm_args,
self.extra_llm_api_options)

Expand Down