Revert "increase default context length to 4096 (#10364)"

This reverts commit 424f648632.
This commit is contained in:
Devon Rifkin 2025-04-28 16:54:11 -07:00 committed by GitHub
parent 5cfc1c39f3
commit dd93e1af85
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 12 additions and 49 deletions

View file

@ -148,7 +148,6 @@ func newScenarioRequest(t *testing.T, ctx context.Context, modelName string, est
successCh: make(chan *runnerRef, 1),
errCh: make(chan error, 1),
}
b.req.opts.NumCtx = 4096
b.srv = &mockLlm{estimatedVRAM: estimatedVRAM, estimatedVRAMByGPU: map[string]uint64{"": estimatedVRAM}}
return b
}