feat(neuralwatt): add GLM 5.2 Fast variant#2662
Closed
monotykamary wants to merge 1 commit into
Closed
Conversation
Add the non-reasoning speed counterpart to GLM 5.2. It mirrors the original glm-5.2 context window, pricing, and modalities, but has reasoning disabled, matching the provider entry in pi-neuralwatt-provider models.json (id: glm-5.2-fast, reasoning: false). Also list the variant in the README Fast Variants section.
Contributor
Author
|
@rekram1-node papi i cant stop |
| @@ -0,0 +1,21 @@ | |||
| name = "GLM 5.2 Fast" | |||
Collaborator
There was a problem hiding this comment.
can u use base model syntax and then override correctly
also reasoning_options are missing
Contributor
Author
There was a problem hiding this comment.
err neuralwatt just makes a separate model endpoint to turn off reasoning 💀
don't kill me papi, i just send the goods
Contributor
|
Closing this pull request as stale because it has not been updated in 7 days after feedback from @rekram1-node. Feel free to reopen it or submit a new pull request if the work is resumed. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Follow-up to #2645. Adds the speed-optimized, non-reasoning counterpart to GLM 5.2.
Context
pi-neuralwatt-providernow exposesglm-5.2-fastas a fast variant of GLM 5.2. Per the provider'smodels.json, it is identical toglm-5.2in context, pricing, and modalities, but hasreasoning: falseand is intended for lower-latency use without thinking.Changes
providers/neuralwatt/models/glm-5.2-fast.tomlname = "GLM 5.2 Fast"reasoning = false(the thinking-capable version remainsglm-5.2)input = 1.45,output = 4.5context = 1_048_560,output = 1_048_5602026-06-18providers/neuralwatt/README.mdglm-5.2-fast — GLM 5.2 Fastto the Fast Variants listValidation
bun validatepasses (exit 0). Generatedproviders.neuralwatt.models["glm-5.2-fast"]entry hasreasoning: falseand the expected cost/limits/modalities.