vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-18 23:49:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
koboldcpp/ggml
History
Ruben Ortlam 75f3bc94e6
Some checks failed
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled
Details
Python check requirements.txt / check-requirements (push) Has been cancelled
Details
Python Type-Check / python type-check (push) Has been cancelled
Details
vulkan: Flash Attention DP4A shader for quantized KV cache (#20797) 
* use integer dot product for quantized KV flash attention

* small improvements

* fix SHMEM_STAGING indexing

* add missing KV type quants

* fixes

* add supported quants to FA tests

* readd fast paths for <8bit quants

* fix mmq gate and shmem checks
2026-04-13 14:21:31 +02:00
..
cmake ggml: backend-agnostic tensor parallelism (experimental) (#19378) 2026-04-09 16:42:19 +02:00
include ggml: backend-agnostic tensor parallelism (experimental) (#19378) 2026-04-09 16:42:19 +02:00
src vulkan: Flash Attention DP4A shader for quantized KV cache (#20797) 2026-04-13 14:21:31 +02:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml: backend-agnostic tensor parallelism (experimental) (#19378) 2026-04-09 16:42:19 +02:00