ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 09:09:50 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
main
ik_llama.cpp/github-data/pull_requests/592 - Another minor readme update.md
Thomas eaa2510a28 Add GitHub data: filename sanitization (#640)
2025-07-23 13:31:53 +02:00

1.1 KiB
Raw Permalink Blame History

🔀 #592 - Another minor readme update

Author saood06
State ✅ Open
Created 2025-07-08
Updated 2025-07-09

Description

I think this looks cleaner.

It does remove mentions to: IQ1_S_R4 PR 492, IQ1_M_R4 PR 494.

They didn't belong in that section, but now I don't know where it would go at all (Features?).

💬 Conversation

👤 ikawrakow commented the 2025-07-09 at 12:00:32:

They didn't belong in that section, but now I don't know where it would go at all (Features?).

They can go under "Quantization additions". IQ1_M_R4 and IQ1_S_R4 are distinct quantization types, not just repacked IQ1_M and IQ1_S.

Not sure if the tabular format for the new models works well. The table is quite squeezed already, and now Hunyuan has been added and dits.llm1 is pending. Do you know how you want to reformat/change to accommodate additional models?