diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-07-27 07:55:01 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-07-27 07:55:01 +0200 |
| commit | 154e0d75fccf1784fe9ff6fd76a630b66563da3d (patch) | |
| tree | 81ce6dbb5b1900c1aa78a879f0593c694cab9d27 /examples/deprecation-warning/README.md | |
| parent | 0684c3e9c70d49323b4fc517128cbe222cab7f96 (diff) | |
Merge mainline llama.cpp (#3)
* Merging mainline - WIP
* Merging mainline - WIP
AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.
* Merging mainline - fix Metal
* Remove check
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/deprecation-warning/README.md')
| -rw-r--r-- | examples/deprecation-warning/README.md | 49 |
1 files changed, 49 insertions, 0 deletions
diff --git a/examples/deprecation-warning/README.md b/examples/deprecation-warning/README.md new file mode 100644 index 00000000..59918ec2 --- /dev/null +++ b/examples/deprecation-warning/README.md @@ -0,0 +1,49 @@ +# Migration notice for binary filenames + +> [!IMPORTANT] +[2024 Jun 12] Binaries have been renamed w/ a `llama-` prefix. `main` is now `llama-cli`, `server` is `llama-server`, etc (https://github.com/ggerganov/llama.cpp/pull/7809) + +This migration was important, but it is a breaking change that may not always be immediately obvious to users. + +Please update all scripts and workflows to use the new binary names. + +| Old Filename | New Filename | +| ---- | ---- | +| main | llama-cli | +| server | llama-server | +| llama-bench | llama-bench | +| embedding | llama-embedding | +| quantize | llama-quantize | +| tokenize | llama-tokenize | +| export-lora | llama-export-lora | +| libllava.a | libllava.a | +| baby-llama | llama-baby-llama | +| batched | llama-batched | +| batched-bench | llama-batched-bench | +| benchmark-matmult | llama-benchmark-matmult | +| convert-llama2c-to-ggml | llama-convert-llama2c-to-ggml | +| eval-callback | llama-eval-callback | +| gbnf-validator | llama-gbnf-validator | +| gguf | llama-gguf | +| gguf-split | llama-gguf-split | +| gritlm | llama-gritlm | +| imatrix | llama-imatrix | +| infill | llama-infill | +| llava-cli | llama-llava-cli | +| lookahead | llama-lookahead | +| lookup | llama-lookup | +| lookup-create | llama-lookup-create | +| lookup-merge | llama-lookup-merge | +| lookup-stats | llama-lookup-stats | +| parallel | llama-parallel | +| passkey | llama-passkey | +| perplexity | llama-perplexity | +| q8dot | llama-q8dot | +| quantize-stats | llama-quantize-stats | +| retrieval | llama-retrieval | +| save-load-state | llama-save-load-state | +| simple | llama-simple | +| speculative | llama-speculative | +| vdot | llama-vdot | +| tests/test-c.o | tests/test-c.o | + |