docs: fix stale --tp flag in bench SGLang examples - #802
Open
imitater-dou wants to merge 3 commits into
Open
Conversation
SGLang 0.5.18 ServerArgs exposes --tp-size (alias --tensor-parallel-size), not --tp. Align the benchmarks README and bench_eagle3 usage docstring with the live CLI and with docs/benchmarks/benchmark.md. Signed-off-by: ADou <ikun3.1415927@gmail.com>
Signed-off-by: ADou <ikun3.1415927@gmail.com>
Signed-off-by: ADou <ikun3.1415927@gmail.com>
3 tasks
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Replace invalid
--tpwith--tp-sizein the SGLanglaunch_serverexamples underbenchmarks/README.mdand thebenchmarks/bench_eagle3.pyusage docstring.SGLang
0.5.18ServerArgsexposes--tp-size(alias--tensor-parallel-size), not--tp. The corrected examples matchdocs/benchmarks/benchmark.mdand the flagsbench_eagle3.pyalready forwards when launching a server.How verified
Against upstream
sgl-project/SpecForgemain SHA2fc993077c3c53df14ebdd5d414c854864476af8and SGLangv0.5.18ServerArgs:tp_sizeCLI flag:--tp-sizewith alias--tensor-parallel-sizeonly (no--tp)sglang==0.5.18inpyproject.tomldocs/benchmarks/benchmark.mdalready uses--tp-size 1bench_eagle3.pylaunch path already passes"--tp-size"fromserver_args.tp_sizeBefore
After