github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-03-09 07:16:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

models: add nemotronh architecture support (#14356)

Browse Source
This commit is contained in:
Jeffrey Morgan
2026-02-22 15:09:14 -08:00
committed by GitHub
parent 06edabdde1
commit 0ade9205cc
22 changed files with 3196 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
server/sched.go
View File

@@ -447,7 +447,7 @@ func (s *Scheduler) load(req *LlmRequest, f *ggml.GGML, systemInfo ml.SystemInfo
// Some architectures are not safe with num_parallel > 1.
// ref: https://github.com/ollama/ollama/issues/4165
if slices.Contains([]string{"mllama", "qwen3vl", "qwen3vlmoe", "qwen3next", "lfm2", "lfm2moe"}, req.model.Config.ModelFamily) && numParallel != 1 {
if slices.Contains([]string{"mllama", "qwen3vl", "qwen3vlmoe", "qwen3next", "lfm2", "lfm2moe", "nemotron_h", "nemotron_h_moe"}, req.model.Config.ModelFamily) && numParallel != 1 {
numParallel = 1
slog.Warn("model architecture does not currently support parallel requests", "architecture", req.model.Config.ModelFamily)
}