Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
0e93ac0b
Unverified
Commit
0e93ac0b
authored
Oct 03, 2025
by
Thomas Parnell
Committed by
GitHub
Oct 03, 2025
Browse files
[CI] Fix distributed hybrid tests in CI (#26155)
Signed-off-by:
Thomas Parnell
<
tpa@zurich.ibm.com
>
parent
5446ad1d
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
2 deletions
+2
-2
tests/models/language/generation/test_hybrid.py
tests/models/language/generation/test_hybrid.py
+2
-2
No files found.
tests/models/language/generation/test_hybrid.py
View file @
0e93ac0b
...
@@ -240,12 +240,12 @@ def test_distributed_correctness(
...
@@ -240,12 +240,12 @@ def test_distributed_correctness(
num_logprobs
:
int
,
num_logprobs
:
int
,
)
->
None
:
)
->
None
:
with
vllm_runner
(
model
,
tensor_parallel_size
=
1
,
with
vllm_runner
(
model
,
tensor_parallel_size
=
1
,
max_num_seqs
=
2
)
as
vllm_model
:
max_num_seqs
=
MAX_NUM_SEQS
)
as
vllm_model
:
vllm_outputs_tp_1
=
vllm_model
.
generate_greedy_logprobs
(
vllm_outputs_tp_1
=
vllm_model
.
generate_greedy_logprobs
(
example_prompts
,
max_tokens
,
num_logprobs
)
example_prompts
,
max_tokens
,
num_logprobs
)
with
vllm_runner
(
model
,
tensor_parallel_size
=
2
,
with
vllm_runner
(
model
,
tensor_parallel_size
=
2
,
max_num_seqs
=
2
)
as
vllm_model
:
max_num_seqs
=
MAX_NUM_SEQS
)
as
vllm_model
:
vllm_outputs_tp_2
=
vllm_model
.
generate_greedy_logprobs
(
vllm_outputs_tp_2
=
vllm_model
.
generate_greedy_logprobs
(
example_prompts
,
max_tokens
,
num_logprobs
)
example_prompts
,
max_tokens
,
num_logprobs
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment