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 #5246] [MERGED] llm: speed up gguf decoding by a lot #11723

New Issue
Closed
opened 2026-04-12 23:37:09 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 23:37:09 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/5246
Author: @bmizerany
Created: 6/24/2024
Status: ✅ Merged
Merged: 6/25/2024
Merged by: @bmizerany

Base: main ← Head: bmizerany/apishowperf

📝 Commits (1)

  • 280d632 llm: speed up gguf decoding by a lot

📊 Changes

13 files changed (+263 additions, -69 deletions)

View changed files

📝 llm/ggla.go (+11 -2)
📝 llm/ggml.go (+18 -7)
➕ llm/ggml_test.go (+1 -0)
📝 llm/gguf.go (+92 -38)
📝 llm/memory_test.go (+11 -8)
📝 llm/server.go (+8 -3)
📝 server/images.go (+1 -1)
📝 server/model.go (+3 -3)
📝 server/routes.go (+16 -3)
📝 server/sched.go (+1 -1)
📝 server/sched_test.go (+3 -3)
➕ util/bufioutil/buffer_seeker.go (+34 -0)
➕ util/bufioutil/buffer_seeker_test.go (+64 -0)

📄 Description

Previously, some costly things were causing the loading of GGUF files
and their metadata and tensor information to be VERY slow:

  • Too many allocations when decoding strings
  • Hitting disk for each read of each key and value, resulting in a
    not-okay amount of syscalls/disk I/O.

The show API is now down to 33ms from 800ms+ for llama3 on a macbook pro
m3.

This commit also prevents collecting large arrays of values when
decoding GGUFs (if desired). When such keys are encountered, their
values are null, and are encoded as such in JSON.

🔄 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/5246 **Author:** [@bmizerany](https://github.com/bmizerany) **Created:** 6/24/2024 **Status:** ✅ Merged **Merged:** 6/25/2024 **Merged by:** [@bmizerany](https://github.com/bmizerany) **Base:** `main` ← **Head:** `bmizerany/apishowperf` --- ### 📝 Commits (1) - [`280d632`](https://github.com/ollama/ollama/commit/280d632982719310cfe896aa7facbb4b20eea817) llm: speed up gguf decoding by a lot ### 📊 Changes **13 files changed** (+263 additions, -69 deletions) <details> <summary>View changed files</summary> 📝 `llm/ggla.go` (+11 -2) 📝 `llm/ggml.go` (+18 -7) ➕ `llm/ggml_test.go` (+1 -0) 📝 `llm/gguf.go` (+92 -38) 📝 `llm/memory_test.go` (+11 -8) 📝 `llm/server.go` (+8 -3) 📝 `server/images.go` (+1 -1) 📝 `server/model.go` (+3 -3) 📝 `server/routes.go` (+16 -3) 📝 `server/sched.go` (+1 -1) 📝 `server/sched_test.go` (+3 -3) ➕ `util/bufioutil/buffer_seeker.go` (+34 -0) ➕ `util/bufioutil/buffer_seeker_test.go` (+64 -0) </details> ### 📄 Description Previously, some costly things were causing the loading of GGUF files and their metadata and tensor information to be VERY slow: * Too many allocations when decoding strings * Hitting disk for each read of each key and value, resulting in a not-okay amount of syscalls/disk I/O. The show API is now down to 33ms from 800ms+ for llama3 on a macbook pro m3. This commit also prevents collecting large arrays of values when decoding GGUFs (if desired). When such keys are encountered, their values are null, and are encoded as such in JSON. --- <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 23:37:09 -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#11723
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?