llama.cpp
ggml-cpu: extend RVV quantization vec dot to higher VLENs
#22754
Open

ggml-cpu: extend RVV quantization vec dot to higher VLENs #22754

rehan-10xengineer
rehan-10xengineer rehan-10xengineer requested a review from ggerganov ggerganov 7 days ago
rehan-10xengineer rehan-10xengineer changed the title 10x/riscv quant vec dot vlens ggml-cpu: extend RVV quantization vec dot to higher VLENs 7 days ago
github-actions github-actions added ggml
taimur-10x ggml-cpu: add rvv 512b,1024b impls for iq4_xs
438f7e34
taimur-10x ggml-cpu: refactor; add rvv 512b, 1024b impls for q6_K, i-quants
dc05e358
RehanQasim-dev ggml-cpu: refactor; add 512 and 1024 implementations of tq3_s, iq3_xx…
1e611d69
taimur-10x taimur-10x force pushed from e3e2c6c8 to 1e611d69 1 day ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone