8000 [DRAFT] Speedup dequantize kernels by dfyz · Pull Request #1221 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

[DRAFT] Speedup dequantize kernels#1221

Closed
dfyz wants to merge 1 commit intoggml-org:masterfrom
dfyz:memory-bound-quantize
Closed

[DRAFT] Speedup dequantize kernels#1221
dfyz wants to merge 1 commit intoggml-org:masterfrom
dfyz:memory-bound-quantize

Commits

Commits on Apr 29, 2023
0