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 #11672] [MERGED] gpt-oss #60300

New Issue
Closed
opened 2026-04-29 15:13:22 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 15:13:22 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/11672
Author: @mxyng
Created: 8/5/2025
Status: ✅ Merged
Merged: 8/5/2025
Merged by: @mxyng

Base: main ← Head: gpt-oss

📝 Commits (10+)

📊 Changes

56 files changed (+6689 additions, -347 deletions)

View changed files

📝 api/types.go (+115 -4)
📝 api/types_test.go (+26 -9)
📝 cmd/cmd.go (+80 -11)
📝 cmd/interactive.go (+20 -6)
📝 convert/convert.go (+2 -0)
➕ convert/convert_gptoss.go (+178 -0)
📝 convert/reader.go (+7 -5)
📝 convert/reader_safetensors.go (+17 -2)
📝 convert/tensor_test.go (+776 -225)
📝 fs/ggml/ggml.go (+20 -1)
📝 fs/ggml/type.go (+13 -5)
📝 llama/patches/0019-metal-add-mean-kernel-14267.patch (+2 -2)
📝 llama/patches/0022-BF16-macos-version-guard.patch (+1 -1)
➕ llama/patches/0023-MXFP4.patch (+1293 -0)
➕ llama/patches/0024-cuda-disable-graph-compat-check-for-OP_ADD.patch (+34 -0)
➕ llama/patches/0025-Disable-ggml-blas-on-macos-v13-and-older.patch (+25 -0)
📝 ml/backend.go (+3 -1)
📝 ml/backend/ggml/ggml.go (+119 -10)
📝 ml/backend/ggml/ggml/include/ggml.h (+1 -1)
📝 ml/backend/ggml/ggml/src/ggml-blas/ggml-blas.cpp (+5 -0)

...and 36 more files

📄 Description

this change adds support for openai's gpt-oss model

🔄 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/11672 **Author:** [@mxyng](https://github.com/mxyng) **Created:** 8/5/2025 **Status:** ✅ Merged **Merged:** 8/5/2025 **Merged by:** [@mxyng](https://github.com/mxyng) **Base:** `main` ← **Head:** `gpt-oss` --- ### 📝 Commits (10+) - [`4a8fc3f`](https://github.com/ollama/ollama/commit/4a8fc3f94594bbd02bcce2867b7b5014160d62e5) bf16 - [`f1c7384`](https://github.com/ollama/ollama/commit/f1c73840d5c72ed7154337958116991d51a199df) tests - [`9950f6e`](https://github.com/ollama/ollama/commit/9950f6ec247952f0b6a7bec758d4484cb9d3d97b) gpt-oss - [`26ade3a`](https://github.com/ollama/ollama/commit/26ade3a34922b0b8416f3a46316d85302d779435) enable gptoss for engine - [`6ca094a`](https://github.com/ollama/ollama/commit/6ca094a3edb32eea9e23d77d8d77ca7789e51577) rough estimate - [`c8ac4cc`](https://github.com/ollama/ollama/commit/c8ac4cc54657c96540804a690b6737b75a1d3727) convert to mxfp4 - [`9679520`](https://github.com/ollama/ollama/commit/9679520e871bf7d6ca1ce457c2d7baae790f49ee) handle safetensors U8 - [`9d1de41`](https://github.com/ollama/ollama/commit/9d1de41b4920f36be9c9cec7b43e44300bfb7cf1) clamp glu/linear - [`9194874`](https://github.com/ollama/ollama/commit/9194874df1994389c90202513c02a0da7e4e7e7c) update tokenizer - [`4fb47ed`](https://github.com/ollama/ollama/commit/4fb47ed36862cead8d9455df8e34ae398d83e29f) MXFP4 support ### 📊 Changes **56 files changed** (+6689 additions, -347 deletions) <details> <summary>View changed files</summary> 📝 `api/types.go` (+115 -4) 📝 `api/types_test.go` (+26 -9) 📝 `cmd/cmd.go` (+80 -11) 📝 `cmd/interactive.go` (+20 -6) 📝 `convert/convert.go` (+2 -0) ➕ `convert/convert_gptoss.go` (+178 -0) 📝 `convert/reader.go` (+7 -5) 📝 `convert/reader_safetensors.go` (+17 -2) 📝 `convert/tensor_test.go` (+776 -225) 📝 `fs/ggml/ggml.go` (+20 -1) 📝 `fs/ggml/type.go` (+13 -5) 📝 `llama/patches/0019-metal-add-mean-kernel-14267.patch` (+2 -2) 📝 `llama/patches/0022-BF16-macos-version-guard.patch` (+1 -1) ➕ `llama/patches/0023-MXFP4.patch` (+1293 -0) ➕ `llama/patches/0024-cuda-disable-graph-compat-check-for-OP_ADD.patch` (+34 -0) ➕ `llama/patches/0025-Disable-ggml-blas-on-macos-v13-and-older.patch` (+25 -0) 📝 `ml/backend.go` (+3 -1) 📝 `ml/backend/ggml/ggml.go` (+119 -10) 📝 `ml/backend/ggml/ggml/include/ggml.h` (+1 -1) 📝 `ml/backend/ggml/ggml/src/ggml-blas/ggml-blas.cpp` (+5 -0) _...and 36 more files_ </details> ### 📄 Description this change adds support for openai's gpt-oss model --- <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 2026-04-29 15:13:22 -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#60300
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?