github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #8731] [CLOSED] Draft: Row Order model definitions #18029

New Issue
Closed
opened 2026-04-16 06:22:32 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 06:22:32 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/8731
Author: @dhiltgen
Created: 1/31/2025
Status: ❌ Closed

Base: jessegross/new_runner ← Head: row_order

📝 Commits (10+)

  • 44b3974 next
  • 5838289 fix linter
  • 3749883 refactor prcess text tests
  • f46a4b0 model: benchmark bpe split
  • c4f127e remove unused file
  • 95eb87a ml: update Dump to handle precision
  • 9a504e2 backend: Don't return an error on Close
  • e0d8f38 backend: Consistently use int (vs. int64) for tensor shapes
  • fdca546 backend: Support graph computation that does not return an output
  • a701c94 ggml-backend: Let GGML allocate context memory

📊 Changes

86 files changed (+478420 additions, -527 deletions)

View changed files

📝 .gitignore (+2 -0)
📝 cmd/cmd.go (+5 -2)
📝 cmd/runner/main.go (+1 -1)
📝 convert/convert.go (+16 -16)
📝 convert/convert_bert.go (+5 -5)
📝 convert/convert_commandr.go (+5 -5)
📝 convert/convert_gemma.go (+5 -5)
📝 convert/convert_gemma2.go (+2 -4)
📝 convert/convert_gemma2_adapter.go (+5 -5)
📝 convert/convert_llama.go (+6 -6)
📝 convert/convert_llama_adapter.go (+5 -5)
📝 convert/convert_mixtral.go (+5 -5)
📝 convert/convert_phi3.go (+7 -7)
📝 convert/convert_qwen2.go (+5 -5)
📝 convert/convert_test.go (+6 -6)
📝 envconfig/config.go (+3 -0)
📝 fs/ggml/ggml.go (+111 -95)
📝 fs/ggml/gguf.go (+6 -7)
📝 fs/ggml/type.go (+2 -7)
📝 fs/util/bufioutil/buffer_seeker.go (+0 -0)

...and 66 more files

📄 Description

Replaced by #9115 on main.

This change switches the model API (and backend) to be row-order.

The GGML backend reverses the shape, and tracks the number of dimensions to handle trailing 1 dimensions.

This also starts to lay some initial foundation for a future change that will add MLX as a second backend.

Keeping this in DRAFT state since only llama3 is converted to row-order - other models will not be functional until they're adjusted following the same pattern.

🔄 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/8731 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 1/31/2025 **Status:** ❌ Closed **Base:** `jessegross/new_runner` ← **Head:** `row_order` --- ### 📝 Commits (10+) - [`44b3974`](https://github.com/ollama/ollama/commit/44b39749d5555b36f2044c08a747886c6bd24fea) next - [`5838289`](https://github.com/ollama/ollama/commit/58382892ad59941dfafc4a4d789343b817b26e74) fix linter - [`3749883`](https://github.com/ollama/ollama/commit/37498836bd5f75a70625670488daf334522b3ad4) refactor prcess text tests - [`f46a4b0`](https://github.com/ollama/ollama/commit/f46a4b07a32c6b4d16f5c51abda714ccbff8fddf) model: benchmark bpe split - [`c4f127e`](https://github.com/ollama/ollama/commit/c4f127ee6d47d1bcea624911cf3ec8f6dfb83540) remove unused file - [`95eb87a`](https://github.com/ollama/ollama/commit/95eb87a0523ced39bf2eb17507cff4901d92bf53) ml: update Dump to handle precision - [`9a504e2`](https://github.com/ollama/ollama/commit/9a504e2f759942cbea9bcd8d270c3273e7e8cc5c) backend: Don't return an error on Close - [`e0d8f38`](https://github.com/ollama/ollama/commit/e0d8f3872aca048b0921f3124ed2351ece3aae81) backend: Consistently use int (vs. int64) for tensor shapes - [`fdca546`](https://github.com/ollama/ollama/commit/fdca5461f1786b262d01d3f922fcd282c32e3b5b) backend: Support graph computation that does not return an output - [`a701c94`](https://github.com/ollama/ollama/commit/a701c9419418716c93642113e8057f1a4efff3ce) ggml-backend: Let GGML allocate context memory ### 📊 Changes **86 files changed** (+478420 additions, -527 deletions) <details> <summary>View changed files</summary> 📝 `.gitignore` (+2 -0) 📝 `cmd/cmd.go` (+5 -2) 📝 `cmd/runner/main.go` (+1 -1) 📝 `convert/convert.go` (+16 -16) 📝 `convert/convert_bert.go` (+5 -5) 📝 `convert/convert_commandr.go` (+5 -5) 📝 `convert/convert_gemma.go` (+5 -5) 📝 `convert/convert_gemma2.go` (+2 -4) 📝 `convert/convert_gemma2_adapter.go` (+5 -5) 📝 `convert/convert_llama.go` (+6 -6) 📝 `convert/convert_llama_adapter.go` (+5 -5) 📝 `convert/convert_mixtral.go` (+5 -5) 📝 `convert/convert_phi3.go` (+7 -7) 📝 `convert/convert_qwen2.go` (+5 -5) 📝 `convert/convert_test.go` (+6 -6) 📝 `envconfig/config.go` (+3 -0) 📝 `fs/ggml/ggml.go` (+111 -95) 📝 `fs/ggml/gguf.go` (+6 -7) 📝 `fs/ggml/type.go` (+2 -7) 📝 `fs/util/bufioutil/buffer_seeker.go` (+0 -0) _...and 66 more files_ </details> ### 📄 Description Replaced by #9115 on main. This change switches the model API (and backend) to be row-order. The GGML backend reverses the shape, and tracks the number of dimensions to handle trailing 1 dimensions. This also starts to lay some initial foundation for a future change that will add MLX as a second backend. Keeping this in DRAFT state since only llama3 is converted to row-order - other models will not be functional until they're adjusted following the same pattern. --- <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 06:22:32 -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#18029
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?