]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 5a46b46)
server-bench : add speed-bench for speculative decoding benchmarking (#23869)
authorRuixiang Wang <redacted>
Fri, 29 May 2026 21:09:47 +0000 (23:09 +0200)
committerGitHub <redacted>
Fri, 29 May 2026 21:09:47 +0000 (23:09 +0200)
commit689a9a470e5d96a853731b2accd463475e5e9a19
tree92311abb629e292306c59afbdc2b3c7adbf893b4tree
parent5a46b46acd9c7adde910f4639dedd9a7d4484c63commit | diff
server-bench : add speed-bench for speculative decoding benchmarking (#23869)

* spec: add speed-bench support for benchmarking

* speed-bench : add trailing newline to requirements.txt

* speed-bench : bump datasets to 4.8.0 to fix ty check

* server-bench : remove now-unused type: ignore after datasets bump
docs/speculative.md diff | blob | history
requirements/requirements-server-bench.txt diff | blob | history
scripts/server-bench.py diff | blob | history
tools/server/bench/speed-bench/README.md [new file with mode: 0644] blob
tools/server/bench/speed-bench/requirements.txt [new file with mode: 0644] blob
tools/server/bench/speed-bench/speed_bench.py [new file with mode: 0644] blob
tools/server/bench/speed-bench/speed_bench_compare.py [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp