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

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

rehan-10xengineer
rehan-10xengineer rehan-10xengineer requested a review from ggerganov ggerganov 41 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 41 days ago
github-actions github-actions added ggml
taimur-10x taimur-10x force pushed from e3e2c6c8 to 1e611d69 35 days ago
taimur-10x taimur-10x force pushed from 1e611d69 to 3db486a2 29 days ago
rehan-10xengineer
xctan
xctan approved these changes on 2026-05-23
taimur-10x taimur-10x force pushed from 3db486a2 to a3bddb36 23 days ago
taimur-10x taimur-10x force pushed from a3bddb36 to 92d3a50b 20 days ago
taimur-10x ggml-cpu: add rvv 512b,1024b impls for iq4_xs
3783a838
taimur-10x ggml-cpu: refactor; add rvv 512b, 1024b impls for q6_K, i-quants
44309858
RehanQasim-dev ggml-cpu: refactor; add 512 and 1024 implementations of tq3_s, iq3_xx…
a29a5ffd
taimur-10x taimur-10x force pushed from 92d3a50b to a29a5ffd 13 days ago
ggerganov ggerganov added merge ready
ggerganov
ggerganov ggerganov merged 3c7450ce into master 12 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone