]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: f478f1b)
ggml-cpu: extend RVV quantization vec dot to higher VLENs (#22754)
authorrehan-10xengineer <redacted>
Thu, 4 Jun 2026 05:03:40 +0000 (10:03 +0500)
committerGitHub <redacted>
Thu, 4 Jun 2026 05:03:40 +0000 (08:03 +0300)
commit3c7450cee1335eef6f8091fa0498e875249e5595
tree35a57d7ebcb780c072d76d64f4459c42a69307cdtree
parentf478f1b6d766683702d3dcba67b6eb02a39d5ec6commit | diff
ggml-cpu: extend RVV quantization vec dot to higher VLENs (#22754)

* ggml-cpu: add rvv 512b,1024b impls for iq4_xs

* ggml-cpu: refactor; add rvv 512b, 1024b impls for q6_K, i-quants

* ggml-cpu: refactor; add 512 and 1024 implementations of tq3_s, iq3_xxs, iq2_s, iq2_xs, iq2_xxs

improve iq2_xs impl for rvv 256

Co-authored-by: Rehan Qasim <redacted>
---------

Co-authored-by: taimur-10x <redacted>
Co-authored-by: Rehan Qasim <redacted>
ggml/src/ggml-cpu/arch/riscv/quants.c diff | blob | history
Packaging of ggml-org/llama.cpp