Skip to content

fix v2 integ#5763

Open
mollyheamazon wants to merge 5 commits intoaws:master-v2from
mollyheamazon:molly/fix-v2-integ
Open

fix v2 integ#5763
mollyheamazon wants to merge 5 commits intoaws:master-v2from
mollyheamazon:molly/fix-v2-integ

Conversation

@mollyheamazon
Copy link
Copy Markdown
Contributor

Issue #, if available:

Description of changes:

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

nargokul and others added 3 commits April 15, 2026 15:23
Replace hardcoded config_name='lmi' in ModelBuilder.optimize() with
the model's dynamically resolved default config name. The JumpStart
metadata for models like llama-3-1-8b-instruct no longer includes an
'lmi' config, causing ValueError during optimization.

Also fix test_jumpstart_session_with_config_name to use the model's
resolved config_name instead of hardcoding 'tgi', and update unit
test assertions in test_js_builder.py accordingly.
The JumpStart metadata update changed the default config from 'lmi' to
'max_context_best_price_performance', which adds extra environment
variables to container_defs. Updated all three test assertions to use
ANY for the Environment dict and separately verify only the specific
env vars each test cares about (OPTION_QUANTIZE, OPTION_TENSOR_PARALLEL_DEGREE,
OPTION_SPECULATIVE_DRAFT_MODEL).
@mollyheamazon mollyheamazon deployed to auto-approve April 16, 2026 06:56 — with GitHub Actions Active
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants