llama.cpp
CUDA: dequant quantized kv on-the-fly for mma kernel
#30202

Open

CUDA: dequant quantized kv on-the-fly for mma kernel #30202

am17an wants to merge 1 commit into master from aman/fa-mma-q-dequant

CUDA: dequant quantized kv on-the-fly for vec kernels

b9e92c43

github-actions added testing

github-actions added ggml

github-actions added CUDA

am17an changed the title ~~CUDA: dequant quantized kv on-the-fly for vec kernels~~ CUDA: dequant quantized kv on-the-fly for mma kernel 37 days ago

Reviewers

No reviews

Assignees

No one assigned

Labels

testing ggml CUDA

Milestone

No milestone

llama.cpp CUDA: dequant quantized kv on-the-fly for mma kernel #30202 Open

CUDA: dequant quantized kv on-the-fly for mma kernel #30202

llama.cpp
CUDA: dequant quantized kv on-the-fly for mma kernel
#30202

Open