[Feat] Support record operations #413
Closed
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
fix ascend attention Co-authored-by: lijiachen19 <[email protected]>
…Group#399) share infra module Co-authored-by: Fang Run <[email protected]>
…ine-Group#401) fix esa to adapt latest NFSStore
Co-authored-by: lijiachen19 <[email protected]>
remove unused cc impl of dramstore
flesher0813
requested review from
FangRun2,
Tarrei,
harrisonyhq,
hek14,
mag1c-h,
qyh111 and
ygwpz
as code owners
* [Fix]remove dram docs and modify quick-start doc * modify index.md --------- Co-authored-by: t00939662 <[email protected]>
…framework (ModelEngine-Group#295) Performance testing tool based on the PyTest testing framework.
flesher0813
force-pushed
the
adapt_metrics_offline
branch
from
c5852e9 to
0e000f6
Compare
ygwpz
reviewed
Nov 27, 2025
ucm/shared/metrics/async_op_db.py
Outdated
| class AsyncUCMOperDB: | ||
| """Asynchronous UCM operation log writer (supports log compression + auto-cleanup)""" | ||
|
|
||
| def _load_config(self, config_path: str) -> Dict[str, Any]: |
Contributor
There was a problem hiding this comment.
can we use unified config.py? because root dir also need config.yaml
ygwpz
reviewed
Nov 27, 2025
| config["kv_block_size"] / 1024 / 1024, | ||
| config["io_size"] / 1024, | ||
| ) | ||
| if role == KVConnectorRole.WORKER and get_tp_group().is_first_rank: |
Contributor
There was a problem hiding this comment.
we need a param to control whether to enable this function.
* [docs]add metrics doc * modify metrics.md * modify metrics.md --------- Co-authored-by: t00939662 <[email protected]>
refactor ucm_connector
* [Feat] Implement kv cache broadcast in MLA in ucm_connector * [Style] Change wait for broadcast into single task method
* add ucm mock connector * fix chunk prefill bug
* [Feat] Support launch from config file * [Docs] Update documents for launch with yaml * [Fix] Change load only on first rank into configuration * [Feat] Add support for hit ratio in yaml * [Fix] Fix load only first rank in non mla scene
refuse monkey patch
fix gqa bug
fix end == 0 bug
optimize generate_tensor
* adapt GQA & modify config.yaml * move process to UCMDirectConnector * fix comment * modify hash function * fix style * code style and modify hash * init parent_block_hash_value
flesher0813
force-pushed
the
adapt_metrics_offline
branch
from
0e000f6 to
e956a06
Compare
flesher0813
requested review from
Wwwzff,
leideng,
pengwwang,
saki-daisuki,
summer-ai007,
wangwenxin0312,
wuhuxiao and
xwLearnsLLM
as code owners
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
10 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.
Purpose
What this PR does / why we need it?
Support users save operation logs to replay trace. When enable using operation db, all load/save operations would be saved in target log_dir.
Modifications
Does this PR introduce any user-facing change?
Support replay traces, and users can modify the yaml file to meet their own needs.
Test
How was this patch tested?