furyhawk/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-07-21 10:15:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md and parameters docs (#1550)

Browse Source 
* Update parameters.md withe recent changes

* Update README.md with recent changes

- Hadamard for V cache
- AVX-VNNI optimizations
- Auto-fit
This commit is contained in:
mcm007
2026-03-29 18:52:08 +02:00
committed by GitHub
parent 46f9f0fb31
commit 028fc79710
2 changed files with 28 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7
View File
@@ -104,6 +104,10 @@ Cuda implementations: `IQ4_KS_R4` and `IQ5_KS_R4` [PR 493](https://github.com/i
CPU [PR 1033](https://github.com/ikawrakow/ik_llama.cpp/pull/1033) and CUDA [PR 1034](https://github.com/ikawrakow/ik_llama.cpp/pull/1034)
##### Hadamard transforms for V-cache
[PR 1527](https://github.com/ikawrakow/ik_llama.cpp/pull/1527)
##### MXFP4 as used in gpt-oss models
Implemented for Zen4, AVX2, ARM_NEON, Metal, CUDA [PR 682](https://github.com/ikawrakow/ik_llama.cpp/pull/682)
@@ -122,11 +126,14 @@ Implemented for Zen4, AVX2, ARM_NEON, Metal, CUDA [PR 682](https://github.com/ik
* Faster `IQ3_KT` and `IQ4_KT` [PR 453](https://github.com/ikawrakow/ik_llama.cpp/pull/453)
* Zen4: Faster PP for `IQ2_KS, IQ4_KS, IQ5_KS` [PR 428](https://github.com/ikawrakow/ik_llama.cpp/pull/428)
* Fast GEMM/GEMV for `IQ1_S` [PR 212](https://github.com/ikawrakow/ik_llama.cpp/pull/212)
* AVX-VNNI optimizations [PR 1446](https://github.com/ikawrakow/ik_llama.cpp/pull/1446) [PR 1455](https://github.com/ikawrakow/ik_llama.cpp/pull/1455) [PR 1467](https://github.com/ikawrakow/ik_llama.cpp/pull/1467) [PR 1474](https://github.com/ikawrakow/ik_llama.cpp/pull/1474) [PR 1482](https://github.com/ikawrakow/ik_llama.cpp/pull/1482)
### Features
* New split mode "graph" for multi GPU setups [PR 1022](https://github.com/ikawrakow/ik_llama.cpp/pull/1022)
* Fused delta-net for Qwen3-Next and Qwen3.5-MoE [PR 1315](https://github.com/ikawrakow/ik_llama.cpp/pull/1315) [PR 1333](https://github.com/ikawrakow/ik_llama.cpp/pull/1333) [PR 1362](https://github.com/ikawrakow/ik_llama.cpp/pull/1362) [PR 1373](https://github.com/ikawrakow/ik_llama.cpp/pull/1373)
* Hadamard transforms for K-cache and V-cache [PR 1033](https://github.com/ikawrakow/ik_llama.cpp/pull/1033) [PR 1034](https://github.com/ikawrakow/ik_llama.cpp/pull/1034) [PR 1527](https://github.com/ikawrakow/ik_llama.cpp/pull/1527)
* Auto-fit offloaded tensors to available VRAM (MoE and dense models) [PR 1501](https://github.com/ikawrakow/ik_llama.cpp/pull/1501) [PR 1504](https://github.com/ikawrakow/ik_llama.cpp/pull/1504)
* Checkpoints for recurrent models [PR 1310](https://github.com/ikawrakow/ik_llama.cpp/pull/1310) [PR 1398](https://github.com/ikawrakow/ik_llama.cpp/pull/1398)
* String ban function for all completions [PR 1185](https://github.com/ikawrakow/ik_llama.cpp/pull/1185) [PR 1243](https://github.com/ikawrakow/ik_llama.cpp/pull/1243)
* OpenAI `/v1/responses` API endpoint [PR 1184](https://github.com/ikawrakow/ik_llama.cpp/pull/1184)