-
Notifications
You must be signed in to change notification settings - Fork 1.6k
[TRTLLM-5530][BREAKING CHANGE] refactor: unify KvCacheConfig in LLM class for pytorch backend #5752
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.
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
base: main
Are you sure you want to change the base?
Conversation
/bot run --disable-fail-fast |
PR_Github #10985 [ run ] triggered by Bot |
PR_Github #10985 [ run ] completed with state |
5df018b
to
d0f6cb0
Compare
/bot run |
PR_Github #11041 [ run ] triggered by Bot |
PR_Github #11041 [ run ] completed with state |
6abe190
to
bf0839b
Compare
/bot run --disable-fail-fast |
1 similar comment
/bot run --disable-fail-fast |
PR_Github #11089 [ run ] triggered by Bot |
/bot kill |
bf0839b
to
f9c7310
Compare
PR_Github #11091 [ kill ] triggered by Bot |
PR_Github #11089 [ run ] completed with state |
PR_Github #11091 [ kill ] completed with state |
/bot run --disable-fail-fast |
PR_Github #11112 [ run ] triggered by Bot |
PR_Github #11112 [ run ] completed with state |
f9c7310
to
67a8191
Compare
/bot run --disable-fail-fast |
PR_Github #11158 [ run ] triggered by Bot |
PR_Github #11158 [ run ] completed with state |
@@ -89,6 +89,9 @@ def get_settings(params: dict, dataset_metadata: DatasetMetadata, model: str, | |||
if extra_llm_api_options: | |||
with open(extra_llm_api_options, 'r') as f: | |||
llm_args_dict = yaml.safe_load(f) | |||
if "kv_cache_config" in llm_args_dict: | |||
kv_cache_dtype = llm_args_dict["kv_cache_config"].get( | |||
"dtype", "auto") | |||
|
|||
if "kv_cache_dtype" in llm_args_dict: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Shouldn't we just augment the retrieval of the dtype in this conditional?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yeah, the "kv_cache_dtype" is merged to KvCacheConfig (a pure python config) as "dtype", so here it tries to fetch it from the kv_cache_config.
67a8191
to
aff5c11
Compare
/bot run |
PR_Github #11247 [ run ] triggered by Bot |
PR_Github #11247 [ run ] completed with state |
aff5c11
to
57dcea6
Compare
/bot run |
PR_Github #11281 [ run ] triggered by Bot |
PR_Github #11281 [ run ] completed with state |
57dcea6
to
fefcca4
Compare
/bot run |
PR_Github #11309 [ run ] triggered by Bot |
PR_Github #11309 [ run ] completed with state |
ff511c3
to
712c60b
Compare
/bot run |
PR_Github #11358 [ run ] triggered by Bot |
PR_Github #11358 [ run ] completed with state |
712c60b
to
d37c6f9
Compare
/bot run --stage-list "A30-PyTorch-2" |
d37c6f9
to
4c7f2e6
Compare
/bot run --stage-list "A30-PyTorch-2" |
PR_Github #11400 [ run ] triggered by Bot |
4c7f2e6
to
5634f17
Compare
/bot run |
PR_Github #11406 [ run ] triggered by Bot |
PR_Github #11400 [ run ] completed with state |
PR_Github #11406 [ run ] completed with state |
/bot run --disable-fail-fast |
PR_Github #11442 [ run ] triggered by Bot |
PR title
Please write the PR title by following template:
[JIRA ticket link/nvbug link/github issue link][fix/feat/doc/infra/...] <summary of this PR>
For example, assume I have a PR hope to support a new feature about cache manager of Jira TRTLLM-1000 ticket, it would be like
[TRTLLM-1000][feat] Support a new feature about cache manager
Description
Please explain the issue and the solution in short.
Test Coverage
GitHub Bot Help
/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...
Provide a user friendly way for developers to interact with a Jenkins server.
Run
/bot [-h|--help]
to print this help message.See details below for each supported subcommand.
run [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]
Launch build/test pipelines. All previously running jobs will be killed.
--disable-fail-fast
(OPTIONAL) : Disable fail fast on build/tests/infra failures.--skip-test
(OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.--stage-list "A10-1, xxx"
(OPTIONAL) : Only run the specified test stages. Examples: "A10-1, xxx". Note: Does NOT update GitHub check status.--gpu-type "A30, H100_PCIe"
(OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.--only-multi-gpu-test
(OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.--disable-multi-gpu-test
(OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.--add-multi-gpu-test
(OPTIONAL) : Force run the multi-GPU tests. Will also run L0 pre-merge pipeline.--post-merge
(OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.--extra-stage "H100_PCIe-[Post-Merge]-1, xxx"
(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-[Post-Merge]-1, xxx".For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.md
.kill
kill
Kill all running builds associated with pull request.
skip
skip --comment COMMENT
Skip testing for latest commit on pull request.
--comment "Reason for skipping build/test"
is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.reuse-pipeline
reuse-pipeline
Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.