Skip to content

Documentation: Add ggml_type value choices for KV cache data type in … #10802

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

Closed
wants to merge 2 commits into from
Closed

Documentation: Add ggml_type value choices for KV cache data type in … #10802

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
59940ef
Documentation: Add ggml_type value choices for KV cache data type in …
MichelleTanPY Dec 12, 2024
92a9392
Updated arg.cpp instead of auto-generated README.md
MichelleTanPY Dec 12, 2024
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
4 changes: 2 additions & 2 deletions examples/server/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,8 +62,8 @@ The project is under active development, and we are [looking for feedback and co
| `--yarn-beta-fast N` | YaRN: low correction dim or beta (default: 32.0)<br/>(env: LLAMA_ARG_YARN_BETA_FAST) |
| `-dkvc, --dump-kv-cache` | verbose print of the KV cache |
| `-nkvo, --no-kv-offload` | disable KV offload<br/>(env: LLAMA_ARG_NO_KV_OFFLOAD) |
| `-ctk, --cache-type-k TYPE` | KV cache data type for K (default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_K) |
| `-ctv, --cache-type-v TYPE` | KV cache data type for V (default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
| `-ctk, --cache-type-k TYPE` | KV cache data type for K (default: f16, f32, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1)<br/>(env: LLAMA_ARG_CACHE_TYPE_K) |
| `-ctv, --cache-type-v TYPE` | KV cache data type for V (default: f16, f32, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
Copy link
Member

@slaren slaren Dec 12, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The list of valid values should be separate from the default value, which is always f16.

Copy link
Collaborator

@ngxson ngxson Dec 12, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You should not manually edit this table. It is generated from arg.cpp and the next time we generate it, your changes will be discarded

Copy link
Contributor Author

@MichelleTanPY MichelleTanPY Dec 12, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Got it. Thanks for reviewing, updated.

| `-dt, --defrag-thold N` | KV cache defragmentation threshold (default: 0.1, < 0 - disabled)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
| `-np, --parallel N` | number of parallel sequences to decode (default: 1)<br/>(env: LLAMA_ARG_N_PARALLEL) |
| `--mlock` | force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
Expand Down
Loading