[CausalLM] Update KVCache save/load #3487
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
EunjuYang
requested review from
DonghakPark,
SeoHyungjun,
again4you,
anyj0527,
baek2sm,
djeong20,
dkjung,
gichan-jang,
haehun,
jaeyun-jung,
jihochu,
jijoongmoon,
leemgs,
lhs8928,
myungjoo,
skykongkong8,
songgot and
wooksong
as code owners
EunjuYang
force-pushed
the
causallm/kv_cache_save
branch
from
51ff92b to
b34fe9e
Compare
- This patch updates KVCache save/load.
- This patch aims to merges the kvcache saving configuration as one
nntr_config.json file.
- In the previous version, we had to update nntr_config.json for the
kv_cache saving and kv_cache using.
- This patch merges the two configurations into one.
- Expected nntr_confg.json
```json
{
...
"system_prompt": {
"head_prompt": "blabla",
"tail_prompt": "blabla",
"kvcache":{ (optional)
"pre_computed_cache_path": "system_prompt_cache_name.bin",
"sys_prompt_token_size"(optional): 512
}
}
```
Signed-off-by: Eunju Yang <[email protected]>
EunjuYang
force-pushed
the
causallm/kv_cache_save
branch
from
b34fe9e to
a41712d
Compare
|
This PR is stale because it has been open 14 days with no activity. Remove stale label or comment or this will be closed in 3 days. |
|
This PR was closed because it has been stalled for 3 days with no activity. |
|
This PR is stale because it has been open 14 days with no activity. Remove stale label or comment or this will be closed in 3 days. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Dependency of the PR
Commits to be reviewed in this PR
{commit-1}
{ ... "system_prompt": { "head_prompt": "blabla", "tail_prompt": "blabla", "kvcache":{ (optional) "pre_computed_cache_path": "system_prompt_cache_name.bin", "sys_prompt_token_size"(optional): 512 } }Self evaluation:
Signed-off-by: Eunju Yang [email protected]
Summary
{ ... "system_prompt"(optional): { "head_prompt": "blabla", "tail_prompt": "blabla", "kvcache"(optional):{ "pre_computed_cache_path": "system_prompt_cache_name.bin", "sys_prompt_token_size"(optional): 512 }, "sample_input": "put your user prompt here" }Signed-off-by: Eunju Yang [email protected]