Skip to content

feat(models): add quantization to novita deepseek mappings#2962

Merged
smakosh merged 1 commit into
theopenco:mainfrom
AmineAce:feat/quant-novita-deepseek
Jul 9, 2026
Merged

feat(models): add quantization to novita deepseek mappings#2962
smakosh merged 1 commit into
theopenco:mainfrom
AmineAce:feat/quant-novita-deepseek

Conversation

@AmineAce

@AmineAce AmineAce commented Jul 9, 2026

Copy link
Copy Markdown
Contributor

Adds quantization to Novita provider mappings in packages/models/src/models/deepseek.ts, per #2946.
Checked every Novita mapping in this file against Novita's own model detail pages. Added the field only where precision was explicitly stated — no inference from model names.

deepseek-v3.2 → fp8
deepseek-v4-flash → fp8

Ran pnpm format; only this file changed.

Summary by CodeRabbit

  • Bug Fixes
    • Updated two model provider configurations to include the correct quantization setting, improving compatibility and consistency for affected DeepSeek model options.

@coderabbitai

coderabbitai Bot commented Jul 9, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Repository UI

Review profile: CHILL

Plan: Pro

Run ID: b7999197-7fc6-4027-8329-5a7a0d44a1d3

📥 Commits

Reviewing files that changed from the base of the PR and between e8a086d and 0461bb1.

📒 Files selected for processing (1)
  • packages/models/src/models/deepseek.ts

Walkthrough

Added quantization: "fp8" field to the novita provider configurations for both the deepseek-v3.2 and deepseek-v4-flash models in the deepseek model definitions file.

Changes

Quantization Field Addition

Layer / File(s) Summary
Add fp8 quantization to novita provider entries
packages/models/src/models/deepseek.ts
Adds quantization: "fp8" field to the novita provider block for both deepseek-v3.2 and deepseek-v4-flash models.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

  • theopenco/llmgateway#2098: Both modify the novita-routed deepseek-v4-flash entry in the same file, with this PR adding the quantization: "fp8" field on top of that provider mapping.
  • theopenco/llmgateway#2956: Both PRs add the quantization: "fp8" field to novita provider entries in the models catalog.
  • theopenco/llmgateway#2946: Both PRs are part of the same quantization field plumbing effort across DeepSeek provider configs.

Suggested reviewers: smakosh

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title accurately summarizes the main change: adding quantization metadata to Novita DeepSeek provider mappings.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

@smakosh smakosh added this pull request to the merge queue Jul 9, 2026
Merged via the queue into theopenco:main with commit 765dbd5 Jul 9, 2026
11 checks passed
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