github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #1761] [MERGED] fix: relay request opts to loaded llm prediction #10660

New Issue
Closed
opened 2026-04-12 23:06:37 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 23:06:37 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/1761
Author: @BruceMacD
Created: 1/2/2024
Status: ✅ Merged
Merged: 1/3/2024
Merged by: @BruceMacD

Base: main ← Head: brucemacd/predict-opts

📝 Commits (7)

  • af385e7 fix: relay request opts to loaded llm prediction
  • 96be73e Update shim_ext_server.go
  • beaa061 ctx as first predict argument
  • b72f42d set options and get model before load
  • c916c80 shared options parsing for requests
  • ae0887d Update ext_server_default.go
  • f28d1b1 fix rebase

📊 Changes

5 files changed (+103 additions, -68 deletions)

View changed files

📝 llm/ext_server_common.go (+18 -18)
📝 llm/ext_server_default.go (+1 -1)
📝 llm/llama.go (+4 -3)
📝 llm/shim_ext_server.go (+1 -1)
📝 server/routes.go (+79 -45)

📄 Description

  • options from the loaded llm were being used regardless of the requested options

Only the options set from the request that initially loaded the model were being used as of the most recent llama.cpp update. Fix this by relaying the resolved options when options are checked during load time.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/1761 **Author:** [@BruceMacD](https://github.com/BruceMacD) **Created:** 1/2/2024 **Status:** ✅ Merged **Merged:** 1/3/2024 **Merged by:** [@BruceMacD](https://github.com/BruceMacD) **Base:** `main` ← **Head:** `brucemacd/predict-opts` --- ### 📝 Commits (7) - [`af385e7`](https://github.com/ollama/ollama/commit/af385e78f71fb530793a77cda20794ff48c974c9) fix: relay request opts to loaded llm prediction - [`96be73e`](https://github.com/ollama/ollama/commit/96be73e6ec0f1cc3da19b2e28893648730040718) Update shim_ext_server.go - [`beaa061`](https://github.com/ollama/ollama/commit/beaa061c5ff0fd447e93782703666c54edcfaa97) ctx as first predict argument - [`b72f42d`](https://github.com/ollama/ollama/commit/b72f42d8032e2277c4d5857b785d54723ee28f52) set options and get model before load - [`c916c80`](https://github.com/ollama/ollama/commit/c916c80281f8deff36edb2b46dddbc358eb36e60) shared options parsing for requests - [`ae0887d`](https://github.com/ollama/ollama/commit/ae0887da4589d9547365a25555603ab3f459c02c) Update ext_server_default.go - [`f28d1b1`](https://github.com/ollama/ollama/commit/f28d1b19d53309cff0b8eaa53e4f75b072489c48) fix rebase ### 📊 Changes **5 files changed** (+103 additions, -68 deletions) <details> <summary>View changed files</summary> 📝 `llm/ext_server_common.go` (+18 -18) 📝 `llm/ext_server_default.go` (+1 -1) 📝 `llm/llama.go` (+4 -3) 📝 `llm/shim_ext_server.go` (+1 -1) 📝 `server/routes.go` (+79 -45) </details> ### 📄 Description - options from the loaded llm were being used regardless of the requested options Only the options set from the request that initially loaded the model were being used as of the most recent llama.cpp update. Fix this by relaying the resolved options when options are checked during load time. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-12 23:06:37 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#10660
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?