Skip to content

[None][doc] Added line about partial reuse #7846

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
thorjohnsen merged 6 commits into from
Dec 5, 2025
Merged

[None][doc] Added line about partial reuse #7846

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
55e852a
Added line about partial reuse
thorjohnsen Sep 18, 2025
e4cff68
Merge branch 'main' into user/tjohnsen/minor_update_kvcache_reuse_leg…
thorjohnsen Sep 18, 2025
caffd1a
Merge branch 'main' into user/tjohnsen/minor_update_kvcache_reuse_leg…
thorjohnsen Sep 19, 2025
206752d
Merge branch 'main' into user/tjohnsen/minor_update_kvcache_reuse_leg…
thorjohnsen Sep 19, 2025
7b437aa
Merge branch 'main' into user/tjohnsen/minor_update_kvcache_reuse_leg…
thorjohnsen Oct 24, 2025
f8922ee
Merge branch 'main' into user/tjohnsen/minor_update_kvcache_reuse_leg…
thorjohnsen Dec 4, 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
2 changes: 1 addition & 1 deletion docs/source/legacy/advanced/kv-cache-reuse.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ There are a few pitfalls that can prevent kv cache reuse when that seems possibl

Kv cache state for system prompts will remain reusable until memory is needed for launching a new request or propagating an existing one. When this happens, reusable blocks are evicted based on LRU. System prompts that are frequently used have a better chance of remaining reusable, but there is no guarantee since launching new requests take priority over possible reuse. Running with a larger batch size, or larger output sequence lengths for example will reduce the probability of kv cache blocks being reused, since it increases memory needs.

KV cache state is stored in blocks, each block holds multiple tokens. Only full blocks can be shared by multiple requests, thus the block size matters. The block size is a trade-off, larger block size may improve efficiency of compute kernels, but it reduces the likelihood of kv cache state reuse. The block defaults to 128 tokens, this can be changed when the model is built with the trtllm-build command, for example
KV cache state is stored in blocks, each block holds multiple tokens. Only full blocks can be shared by multiple requests, thus the block size matters. Partially matched blocks can also be reused, but that creates a new copy of the block for each sequence. The block size is a trade-off, larger block size may improve efficiency of compute kernels, but it reduces the likelihood of kv cache state reuse. The block defaults to 128 tokens, this can be changed when the model is built with the trtllm-build command, for example

```trtllm-build --tokens_per_block 32 ...```

Expand Down