ochafik/llama.cpp

Pull Requests Commits

Merge remote-tracking branch 'origin/master' into json-faster-repetitions

ochafik committed 1 year ago

54461ffa

json: fix regexp repeats + port changes + fix date strings

ochafik committed 1 year ago

91a0ee78

quantize : fix precedence of cli args (#6541)

ggerganov committed 1 year ago

Verified b73e564b

llama : support negative ith in llama_get_ API (#6519)

TheFlipbook committed 1 year ago

Verified e3c337d8

llama : save and restore kv cache for single seq id (#6341)

kaetemi committed 1 year ago

Verified beea6e1b

remove row=1 cond (#6532)

abhilash1910 committed 2 years ago

Verified 87fb5b42

Adding KodiBot to UI list (#6535)

firatkiral committed 2 years ago

Verified d752327c

Change Windows AMD example to release build to make inference much faster. (#6525)

thebaron88 committed 2 years ago

Verified 855f5440

flake.lock: Update (#6517)

ggerganov committed 2 years ago

Verified b909236c

Add GritLM as supported models. (#6513)

dranger003 committed 2 years ago

Verified e0717e75

ggerganov committed 2 years ago

Verified c3724779

ggml: bypass code incompatible with CUDA < 11.1 (whisper/2020)

primenko-v committed 2 years ago

Verified f77261a7

scripts : sync ggml-cuda folder

ggerganov committed 2 years ago

Verified 43e8995e

Run make to build the project (#6457)

limitedAtonement committed 2 years ago

Verified 9472bce3

support/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS, GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ3_S, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M (#6521)

NeoZhangJianyu committed 2 years ago

Verified d4f220a5

ggerganov committed 2 years ago

Verified 54ea0698

backend : fix typo in scheduler documentation (ggml/781)

danbev committed 2 years ago

Verified b66aec67

Tests: Added integration tests for GBNF parser (#6472)

HanClinto committed 2 years ago

Verified 57dd02c4

ci: bench: support sse and fix prompt processing time / server: add tokens usage in stream OAI response (#6495)

phymbert committed 2 years ago

Verified 75cd4c77

gguf.py : add licence and version to gguf writer (#6504)

mofosyne committed 2 years ago

Verified a8bd14d5

readme : update UI list (#6503)

hugo53 committed 2 years ago

Verified d0f5deeb

bench : make n_batch and n_ubatch configurable in Batched bench (#6500)

Sunt-ing committed 2 years ago

Verified 87e21bba

json: port repetitions to JS

ochafik committed 2 years ago

8ab67144

[SYCL] Fixed minor bug when enabling FP16 for non intel targets (#6464)

OuadiElfarouki committed 2 years ago

Verified 1b496a74

json: fix / speed up regexp pattern repetitions

ochafik committed 2 years ago

1dae0896

json: rm debug code

ochafik committed 2 years ago

902273ff

json: improved repetitions & builtin rule deps

ochafik committed 2 years ago

375f85dd

readme : add Dot to UI list (#6487)

alexpinel committed 2 years ago

Verified a307375c

readme : fix typo (#6481)

junnjiee committed 2 years ago

Verified b660a572

server: add cURL support to server Dockerfiles (#6474)

elepedus committed 2 years ago

Verified 0a1d889e

Older