github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 14:13:13 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #15114] Improve https://github.com/ollama/ollama/pull/14864 (Update to b8457 ) #40905

New Issue
Open
opened 2026-04-23 01:41:28 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-23 01:41:28 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/15114
Author: @inforithmics
Created: 3/28/2026
Status: 🔄 Open

Base: main ← Head: ImproveGgmlUpdate

📝 Commits (10+)

  • a4c0137 ggml: update to 0beb8db3a0
  • 2641450 Allow more time for discovery
  • 2647195 Performance fixes
  • ed8bd81 Merge remote-tracking branch 'upstream/main' into ImproveGgmlUpdate
  • 48b950d Merge remote-tracking branch 'upstream/main' into ImproveGgmlUpdate
  • 9ab47f9 Update to b8308
  • c172e25 Remove ggml metal solve tri patch
  • 7c1f6a4 added reasoning-budget to .rsync
  • 4ff1871 fixing solar patch
  • c5e2ad9 trying to fix ci (golang lint)

📊 Changes

425 files changed (+48179 additions, -15000 deletions)

View changed files

📝 .github/workflows/release.yaml (+1 -1)
📝 .github/workflows/test.yaml (+4 -1)
📝 CMakePresets.json (+16 -1)
📝 Makefile.sync (+38 -3)
📝 discover/runner.go (+7 -13)
📝 integration/embed_test.go (+12 -2)
📝 integration/tools_test.go (+8 -3)
📝 kvcache/causal.go (+4 -1)
📝 llama/README.md (+26 -24)
📝 llama/build-info.cpp (+1 -1)
📝 llama/llama.cpp/.rsync-filter (+6 -0)
📝 llama/llama.cpp/LICENSE (+1 -1)
📝 llama/llama.cpp/common/common.cpp (+140 -163)
📝 llama/llama.cpp/common/common.go (+1 -1)
📝 llama/llama.cpp/common/common.h (+238 -87)
📝 llama/llama.cpp/common/json-schema-to-grammar.cpp (+87 -66)
➕ llama/llama.cpp/common/peg-parser.cpp (+2030 -0)
➕ llama/llama.cpp/common/peg-parser.h (+510 -0)
➕ llama/llama.cpp/common/reasoning-budget.cpp (+263 -0)
➕ llama/llama.cpp/common/reasoning-budget.h (+53 -0)

...and 80 more files

📄 Description

Improve https://github.com/ollama/ollama/pull/14864 with my sugested changes

  1. Update with Main
  2. Update llama.cpp to b8308 Intel Vulkan Driver fixes
  3. Removed the 0033-ggml-metal-solve_tri.patch. I think it is now fully supported in the vendor code
  4. Added reasonining-budget.* to rsync filter
  5. Fixed Solar-pro patch
  6. Fix Go lint in CI
  7. Update to b8317(Gated delta net op support in Vulkan)
  8. Update to b8399(vulkan: disable mmvq on Intel Windows Driver)
  9. Fixed Export Gpu UUID patch
  10. Added mtmd-debug to rsync filter
  11. Updated to b8457 (Vulkan: improved delta net)
  12. Adapted sampling_ext.cpp

🔄 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/15114 **Author:** [@inforithmics](https://github.com/inforithmics) **Created:** 3/28/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `ImproveGgmlUpdate` --- ### 📝 Commits (10+) - [`a4c0137`](https://github.com/ollama/ollama/commit/a4c01378cc05fb3c9ecc54d614cbf255e116352b) ggml: update to 0beb8db3a0 - [`2641450`](https://github.com/ollama/ollama/commit/2641450885b2c838625eb706a3ed18cbb68008cf) Allow more time for discovery - [`2647195`](https://github.com/ollama/ollama/commit/264719513c109111c8f8abea82161bed73559bbc) Performance fixes - [`ed8bd81`](https://github.com/ollama/ollama/commit/ed8bd8123ebb32b6e27f1dcfb983081fceec05b1) Merge remote-tracking branch 'upstream/main' into ImproveGgmlUpdate - [`48b950d`](https://github.com/ollama/ollama/commit/48b950d532a24f730f8d6ef03a30b4b81451c9cf) Merge remote-tracking branch 'upstream/main' into ImproveGgmlUpdate - [`9ab47f9`](https://github.com/ollama/ollama/commit/9ab47f9f3838618e7591fc499562a4e45930fd0f) Update to b8308 - [`c172e25`](https://github.com/ollama/ollama/commit/c172e25a2cf6bfe49324acc6e9f4bbd4c3c0e852) Remove ggml metal solve tri patch - [`7c1f6a4`](https://github.com/ollama/ollama/commit/7c1f6a4b2b4c0c6157f2b3545f5a2a7bdcd73a1c) added reasoning-budget to .rsync - [`4ff1871`](https://github.com/ollama/ollama/commit/4ff1871c7a04f1f3c86c8f72fc533e00a3eca52b) fixing solar patch - [`c5e2ad9`](https://github.com/ollama/ollama/commit/c5e2ad99e817f77b2bf8c141865012a2d4a472bf) trying to fix ci (golang lint) ### 📊 Changes **425 files changed** (+48179 additions, -15000 deletions) <details> <summary>View changed files</summary> 📝 `.github/workflows/release.yaml` (+1 -1) 📝 `.github/workflows/test.yaml` (+4 -1) 📝 `CMakePresets.json` (+16 -1) 📝 `Makefile.sync` (+38 -3) 📝 `discover/runner.go` (+7 -13) 📝 `integration/embed_test.go` (+12 -2) 📝 `integration/tools_test.go` (+8 -3) 📝 `kvcache/causal.go` (+4 -1) 📝 `llama/README.md` (+26 -24) 📝 `llama/build-info.cpp` (+1 -1) 📝 `llama/llama.cpp/.rsync-filter` (+6 -0) 📝 `llama/llama.cpp/LICENSE` (+1 -1) 📝 `llama/llama.cpp/common/common.cpp` (+140 -163) 📝 `llama/llama.cpp/common/common.go` (+1 -1) 📝 `llama/llama.cpp/common/common.h` (+238 -87) 📝 `llama/llama.cpp/common/json-schema-to-grammar.cpp` (+87 -66) ➕ `llama/llama.cpp/common/peg-parser.cpp` (+2030 -0) ➕ `llama/llama.cpp/common/peg-parser.h` (+510 -0) ➕ `llama/llama.cpp/common/reasoning-budget.cpp` (+263 -0) ➕ `llama/llama.cpp/common/reasoning-budget.h` (+53 -0) _...and 80 more files_ </details> ### 📄 Description Improve https://github.com/ollama/ollama/pull/14864 with my sugested changes 1. Update with Main 2. Update llama.cpp to b8308 Intel Vulkan Driver fixes 3. Removed the 0033-ggml-metal-solve_tri.patch. I think it is now fully supported in the vendor code 4. Added reasonining-budget.* to rsync filter 5. Fixed Solar-pro patch 6. Fix Go lint in CI 7. Update to b8317(Gated delta net op support in Vulkan) 8. Update to b8399(vulkan: disable mmvq on Intel Windows Driver) 9. Fixed Export Gpu UUID patch 10. Added mtmd-debug to rsync filter 11. Updated to b8457 (Vulkan: improved delta net) 12. Adapted sampling_ext.cpp --- <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 2026-04-23 01:41:29 -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#40905
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?