ggerganov/llama.cpp

Pull Requests Commits

airMeng committed 353 days ago

d32a8f61

seperate DPCT helpers outside

airMeng committed 354 days ago

1f80e0e4

github: add contact links to issues and convert question into research [no ci] (#7612)

mofosyne committed 354 days ago

Verified e6157f94

Move convert.py to examples/convert-legacy-llama.py (#7430)

Galunid committed 354 days ago

Verified 9c4c9cc8

faster avx512 exp implementation (#7551)

chriselrod committed 354 days ago

Verified 59b0d077

ggml : fix loongarch build (O2 issue) (#7636)

junchao-loongson committed 354 days ago

Verified d5c05821

README: explain parallel build [no ci] (#7618)

JohannesGaessler committed 354 days ago

Verified 972b555a

[SYCL] fix intel docker (#7630)

airMeng committed 354 days ago

Verified 3854c9d0

gguf-py : Add tokenizer.ggml.pre to gguf-new-metadata.py (#7627)

Galunid committed 355 days ago

Verified eb57fee5

metal : remove invalid asserts (#7617)

ggerganov committed 355 days ago

Verified 55d62262

metal : add missing asserts (#7617)

ggerganov committed 355 days ago

Verified 975ec63f

ggml : fix YARN + add tests + add asserts (#7617)

ggerganov committed 355 days ago

Verified fb76ec31

cuda : non-cont concat support (#7610)

ggerganov committed 355 days ago

Verified cce3dcff

llama-bench : add support for the RPC backend (#7435)

rgerganov committed 355 days ago

Verified 210d9917

ggml : use atomic_flag for critical section (#7598)

slaren committed 355 days ago

Verified 87bdf2a1

scripts : remove mpi remnants

ggerganov committed 355 days ago

Verified 00281b7b

ggerganov committed 355 days ago

Verified 2ab97728

ggml : restore ggml_rope_xpos_inplace (ggml/0)

ggerganov committed 355 days ago

Verified 72de268b

Add Arc A750 and Arch linux to readme-sycl.md as verified GPU model and Linux distro (#7605)

Akarshan Biswas committed 355 days ago

Verified 0e8d8bfd

ggml : fix typo in ggml.c (#7603)

zhouwg committed 356 days ago

Verified 504f0c34

[SYCL] Align GEMM dispatch (#7566)

airMeng committed 356 days ago

Verified b864b50c

Tokenizer WPM fixes (#7500)

jaime-m-p committed 356 days ago

Verified 02c1ecad

sycl : fix assert (#7563)

ggerganov committed 356 days ago

Verified 6bd12ce4

llama : support small Granite models (#7481)

giuseppe committed 356 days ago

Verified 5442939f

vulkan: properly initialize vulkan devices for LLAMA_SPLIT_MODE_NONE (#7552)

Adriankhl committed 356 days ago

Verified 56411a95

rpc : resource management rework (#7562)

rgerganov committed 356 days ago

Verified 2b737caa

Add support for DeepseekV2ForCausalLM (#7519)

fairydreaming committed 356 days ago

Verified ee3dff6b

tests : fix test-tokenizer-0.sh

ggerganov committed 356 days ago

Verified edc29433

llama : handle unknown utf8 bytes (#7588)

ggerganov committed 356 days ago

Verified 8b99e2aa

github: add refactor to issue template (#7561)

mofosyne committed 356 days ago

Verified 271ff3fc

Older