]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)
authorXuan Son Nguyen <redacted>
Fri, 18 Oct 2024 21:18:01 +0000 (23:18 +0200)
committerGitHub <redacted>
Fri, 18 Oct 2024 21:18:01 +0000 (23:18 +0200)
commitcda0e4b648dde8fac162b3430b14a99597d3d74f
tree57f3df961f01b6302d85bf12bdceb1447ab06c8e
parentafd9909a6481402844aecefa8a8908afdd7f52f1
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

* refactor llama_batch_get_one

* adapt all examples

* fix simple.cpp

* fix llama_bench

* fix

* fix context shifting

* free batch before return

* use common_batch_add, reuse llama_batch in loop

* null terminated seq_id list

* fix save-load-state example

* fix perplexity

* correct token pos in llama_batch_allocr
22 files changed:
common/common.cpp
examples/batched-bench/batched-bench.cpp
examples/cvector-generator/cvector-generator.cpp
examples/eval-callback/eval-callback.cpp
examples/imatrix/imatrix.cpp
examples/infill/infill.cpp
examples/llama-bench/llama-bench.cpp
examples/llama.android/llama/src/main/cpp/llama-android.cpp
examples/llava/llava-cli.cpp
examples/llava/llava.cpp
examples/llava/minicpmv-cli.cpp
examples/lookahead/lookahead.cpp
examples/lookup/lookup.cpp
examples/main/main.cpp
examples/parallel/parallel.cpp
examples/perplexity/perplexity.cpp
examples/save-load-state/save-load-state.cpp
examples/server/server.cpp
examples/simple/simple.cpp
examples/speculative/speculative.cpp
include/llama.h
src/llama.cpp