Trace File Refactor#829
Conversation
|
Hi @SkiHatDuckie, the DCO check has failed. Please click on DCO in the Checks section for instructions on how to resolve this. |
|
Sorry, messed up the rebase. Give me a minute while I clean up the history. |
52e2b60 to
7a1e3c5
Compare
dbutenhof
left a comment
There was a problem hiding this comment.
Just logging a few doc comments I caught in a quick scan. I'll get to the code tomorrow morning...
|
Hi @SkiHatDuckie, the DCO check has failed. Please click on DCO in the Checks section for instructions on how to resolve this. |
3aab3ac to
283cfff
Compare
|
Congrats on breaking the |
…#855) ## Summary This is a separate PR for the bug fix contained in #829, if we instead wish to just get the bug fix in for v0.7.0. This will be closed if the trace file refactor is merged, or after the release of v0.7.0. ## Details - Fixed a bug with Mooncake format not working with multiprocessing ## Related Issues - This is also fixed with #829 --- - [x] "I certify that all code in this PR is my own, except as noted below." ## Use of AI - [ ] Includes code generated or substantially modified by an AI agent - [ ] Includes tests generated or substantially modified by an AI agent > NOTE: the `Generated-by` or `Assisted-by` trailers should be used in git commit messages when code or tests were generated or substantially modified by an AI agent, as described in the project's [`DEVELOPING.md`](https://github.com/vllm-project/guidellm/blob/main/DEVELOPING.md) file. --- # git log commit 3b89ec2 Author: SkiHatDuckie <SkiHatDuckie@gmail.com> Date: Thu Jun 25 11:54:24 2026 -0400 Hotfix: Add relative_timestamp column to output in Mooncake deserializer Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com> commit 8d2cba0 Author: SkiHatDuckie <SkiHatDuckie@gmail.com> Date: Thu Jun 25 12:59:10 2026 -0400 Move `timestamps` outside the loop Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com> --------- Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
sjmonson
left a comment
There was a problem hiding this comment.
My bad, meant to post this morning. This PR also needs another rebase (hopefully the last one) and also some tests are failing.
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
jaredoconnell
left a comment
There was a problem hiding this comment.
It looks good, and I tested it and it worked. I have a few comments.
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
dbutenhof
left a comment
There was a problem hiding this comment.
There's a broken .md link after you renamed a header: that should be fixed. I don't think any of the other comments are pressing...
jaredoconnell
left a comment
There was a problem hiding this comment.
Looks ready for merging once Dave's comments are addressed.
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
Signed-off-by: SkiHatDuckie <SkiHatDuckie@gmail.com>
|
Queued — the merge queue status continues in this comment ↓. |
Merge Queue Status
This pull request spent 5 minutes 25 seconds in the queue, including 4 minutes 58 seconds running CI. Required conditions to merge
|
Summary
A refactoring of trace formats that separates format-agnostic trace replay functionality from format-specific functionality. Notably, all formats now work with the same dataset deserializer. Two abstract classes
TraceDataArgsandTraceFormatBaseare required to be implemented by all formats instead.Additional documentation has been added to better cover all supported trace formats and their different requirements.
The unique prefixes for cache resistance found originally in
trace_synthetic.py(nowtrace_minimal.py) was removed due to being incompatible with the new model. It may be re-added as a feature in future PRs through another means.Details
trace_common.pyTraceDatasetDeserializergenerate_token_idsanddecode_prompttotrace_common.pyTraceDataArgs: an abstract class inherited by all formatsTraceFormatBaseandTraceFormatRegistry: defines an interface for format-specific requirements and functionality on top ofTraceExamplesIterableTraceSyntheticDatasetDeserializerandTraceSyntheticDataArgswithMinimalTraceFormatandMinimalTraceFormatArgsTraceMooncakeDatasetDeserializerandTraceMooncakeDataArgswithMooncakeTraceFormatandMooncakeTraceFormatArgstrace_synthetic.py->trace_minimal.pytest_trace_synthetic.py->test_trace_minimal.pytest_trace_common.py, and rearranged preexisting tests accordinglytest_replay_profile.py,test_trace_replay.pyandtest_trace_replay_multiprocess.pyIterableDatasetfor streamingtrace_file_formats.mdto cover all trace formats supported by GuideLLMgetting_started/benchmark.mdandguides/datasets.mddata/deserializers/__init__.pyload_trace_rowstrace_minimal.pyTest Plan
tox -e test-unittox -e test-integrationtox -e lint-check && tox -e type-checkRelated Issues
Use of AI
git log
commit 027f439
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 15 12:16:03 2026 -0400
commit 6ec92f5
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 15 13:00:51 2026 -0400
commit 76f43df
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 15 15:11:25 2026 -0400
commit d79be07
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 16 09:38:05 2026 -0400
commit 00ccea7
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 16 09:58:18 2026 -0400
commit 7de32d6
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 16 16:58:54 2026 -0400
commit 6f6e464
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Wed Jun 17 10:57:16 2026 -0400
commit 9cd8729
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Wed Jun 17 16:34:10 2026 -0400
commit 26b740f
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Thu Jun 18 15:09:33 2026 -0400
commit 7911a87
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Thu Jun 18 16:16:15 2026 -0400
commit 9aea389
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Thu Jun 18 16:18:38 2026 -0400
commit 27687b2
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Thu Jun 18 16:25:29 2026 -0400
commit 73b2eda
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 22 11:04:41 2026 -0400
commit 2cdb3b8
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 22 11:15:03 2026 -0400
commit 04626fe
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 22 11:28:35 2026 -0400
commit 8f1ab50
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 22 11:49:30 2026 -0400
commit dff58aa
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 22 12:20:30 2026 -0400
commit 342bd0c
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 22 16:12:02 2026 -0400
commit 37f3b10
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 22 16:17:20 2026 -0400
commit 7bc2f96
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Wed Jun 24 10:07:04 2026 -0400
commit e0fe688
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Wed Jun 24 10:47:16 2026 -0400
commit 955a8f5
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Wed Jun 24 11:31:31 2026 -0400
commit 8908132
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Wed Jun 24 11:35:31 2026 -0400
commit e344e80
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Thu Jun 25 13:00:26 2026 -0400
commit 1e842a4
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 29 17:16:23 2026 -0400
commit f68217f
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 29 17:20:50 2026 -0400
commit 73617d1
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Mon Jun 29 17:50:56 2026 -0400
commit d6f0e67
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 30 08:59:31 2026 -0400
commit 9dd48e4
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 30 10:04:58 2026 -0400
commit f32a01e
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 30 10:17:55 2026 -0400
commit 5c51338
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 30 10:29:43 2026 -0400
commit 9edb490
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 30 10:35:10 2026 -0400
commit 9a2c7c1
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 30 12:50:13 2026 -0400
commit 8346b53
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 30 12:57:04 2026 -0400
commit 2741e11
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 30 13:04:58 2026 -0400
commit 5b955d1
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 30 13:07:47 2026 -0400
commit 00efe7b
Author: SkiHatDuckie SkiHatDuckie@gmail.com
Date: Tue Jun 30 13:10:04 2026 -0400
Signed-off-by: SkiHatDuckie SkiHatDuckie@gmail.com