[PR #638] [MERGED] fix KExpertsMarlin on GPU with out CUDA Graph #1438

New issue

Closed

opened 2026-10-29 14:52:27 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-29 14:52:27 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/kvcache-ai/ktransformers/pull/638
Author: @Atream
Created: 2/24/2025
Status: ✅ Merged
Merged: 2/24/2025
Merged by: @Atream

Base: main ← Head: feat-moonlight

📝 Commits (1)

f327695 fix KExpertsMarlin on GPU with out CUDA Graph

📊 Changes

2 files changed (+13 additions, -0 deletions)

View changed files

📝 ktransformers/optimize/optimize_rules/Moonlight-16B-A3B.yaml (+11 -0)
📝 ktransformers/util/custom_gguf.py (+2 -0)

📄 Description

No description provided

_{🔄 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/kvcache-ai/ktransformers/pull/638 **Author:** [@Atream](https://github.com/Atream) **Created:** 2/24/2025 **Status:** ✅ Merged **Merged:** 2/24/2025 **Merged by:** [@Atream](https://github.com/Atream) **Base:** `main` ← **Head:** `feat-moonlight` --- ### 📝 Commits (1) - [`f327695`](https://github.com/kvcache-ai/ktransformers/commit/f327695079298e703e24eb8a9f2493fe4e2bde80) fix KExpertsMarlin on GPU with out CUDA Graph ### 📊 Changes **2 files changed** (+13 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `ktransformers/optimize/optimize_rules/Moonlight-16B-A3B.yaml` (+11 -0) 📝 `ktransformers/util/custom_gguf.py` (+2 -0) </details> ### 📄 Description _No description provided_ --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-29 14:52:27 +00:00