github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #62] [CLOSED] llama: replace bindings with llama_* calls #15228

New Issue
Closed
opened 2026-04-16 04:53:34 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 04:53:34 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/62
Author: @jmorganca
Created: 7/10/2023
Status: ❌ Closed

Base: main ← Head: b2

📝 Commits (3)

  • dfcef1a llama: replace bindings with llama_* calls
  • 642cd63 do not panic on diconnect
  • 234577b Merge pull request #64 from jmorganca/b2-nopanic

📊 Changes

10 files changed (+101 additions, -983 deletions)

View changed files

📝 api/types.go (+1 -1)
📝 llama/CMakeLists.txt (+5 -6)
➖ llama/binding/binding.cpp (+0 -705)
➖ llama/binding/binding.h (+0 -61)
📝 llama/llama.go (+76 -172)
➖ llama/llama_cublas.go (+0 -9)
➖ llama/llama_metal.go (+0 -2)
➖ llama/llama_openblas.go (+0 -9)
📝 llama/options.go (+1 -1)
📝 server/routes.go (+18 -17)

📄 Description

Early PR to replace the C++ binding files with direct calls to llama.cpp from Go. It's missing quite a few features the C++ binding.cpp files had although those were almost direct copies of the main example in llama.cpp's repo. We should be able to add them back relatively easily. It's most likely slower as well so we'll have to make sure it's as fast / faster than the bindings or c++ example implementation.

🔄 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/62 **Author:** [@jmorganca](https://github.com/jmorganca) **Created:** 7/10/2023 **Status:** ❌ Closed **Base:** `main` ← **Head:** `b2` --- ### 📝 Commits (3) - [`dfcef1a`](https://github.com/ollama/ollama/commit/dfcef1a8843e943e1e17c4ff8c3cfb82e2fde8e5) llama: replace bindings with `llama_*` calls - [`642cd63`](https://github.com/ollama/ollama/commit/642cd63759e602a2a8f6148fde05ddfb9820af07) do not panic on diconnect - [`234577b`](https://github.com/ollama/ollama/commit/234577bdb2dd0fd3174ea24413250109dbd5618e) Merge pull request #64 from jmorganca/b2-nopanic ### 📊 Changes **10 files changed** (+101 additions, -983 deletions) <details> <summary>View changed files</summary> 📝 `api/types.go` (+1 -1) 📝 `llama/CMakeLists.txt` (+5 -6) ➖ `llama/binding/binding.cpp` (+0 -705) ➖ `llama/binding/binding.h` (+0 -61) 📝 `llama/llama.go` (+76 -172) ➖ `llama/llama_cublas.go` (+0 -9) ➖ `llama/llama_metal.go` (+0 -2) ➖ `llama/llama_openblas.go` (+0 -9) 📝 `llama/options.go` (+1 -1) 📝 `server/routes.go` (+18 -17) </details> ### 📄 Description Early PR to replace the C++ binding files with direct calls to llama.cpp from Go. It's missing quite a few features the C++ `binding.cpp` files had although those were almost direct copies of the `main` example in llama.cpp's repo. We should be able to add them back relatively easily. It's most likely slower as well so we'll have to make sure it's as fast / faster than the bindings or c++ example implementation. --- <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 2026-04-16 04:53:34 -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#15228
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?