ochafik/llama.cpp

Pull Requests Commits

Don't use sccache for HIP windows builds

ochafik committed 1 year ago

a967723f

set CMAKE_HIP_COMPILER_LAUNCHER env var, not cmake var

Olivier Chafik committed 1 year ago

9fc1ed18

ci: attempt to use sccache + HIP

Olivier Chafik committed 1 year ago

7a8bb507

`ci`: use sccache on windows instead of ccache (#11545)

ochafik committed 1 year ago

Verified aa6fb132

`tool-call`: fix llama 3.x and functionary 3.2, play nice w/ pydantic_ai package, update readme (#11539)

ochafik committed 1 year ago

Verified a83f5286

fix stop regression (#11543)

ochafik committed 1 year ago

Verified b1bcd309

Fix chatml fallback for unsupported builtin templates (when --jinja not enabled) (#11533)

ochafik committed 1 year ago

Verified 5783575c

server : fix --jinja when there's no tools or schema (typo was forcing JSON) (#11531)

ochafik committed 1 year ago

Verified 4a2b196d

common: Add missing va_end (#11529)

stevegrubb committed 1 year ago

Verified 1bd3047a

server : update help metrics processing/deferred (#11512)

danbev committed 1 year ago

Verified a2df2787

`ci`: ccache for all github worfklows (#11516)

ochafik committed 1 year ago

Verified 553f1e46

Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)

ochafik committed 1 year ago

Verified 8b576b6c

HIP: require at least HIP 5.5

IMbackK committed 1 year ago

27d135c9

HIP: Prepare reduction operators for wave 64

IMbackK committed 1 year ago

6af1ca48

CUDA/HIP: add warp_size to cuda_device_info

IMbackK committed 1 year ago

c300e68e

sync: minja (#11499)

ochafik committed 1 year ago

Verified 3d804dec

vocab : correctly identify LF token for GPT-2 style BPE tokenizer (#11496)

mgroeber9110 committed 1 year ago

Verified ffd0821c

server : use lambda instead of std::bind (#11507)

danbev committed 1 year ago

Verified 4314e56c

server : (docs) added response format for /apply-template [no ci] (#11503)

isaac-mcfadyen committed 1 year ago

Verified 496e5bf4

readme : reference examples relative links (#11505)

guspan-tanadi committed 1 year ago

Verified 7919256c

server : update json snippets in README.md [no ci] (#11492)

danbev committed 1 year ago

Verified e0449763

server : add /apply-template endpoint for additional use cases of Minja functionality (#11489)

pnb committed 1 year ago

Verified eb7cf15a

vulkan: implement initial support for IQ2 and IQ3 quantizations (#11360)

remyoudompheng committed 1 year ago

Verified 66ee4f29

server : update auto gen files comments [no ci] (#11484)

danbev committed 1 year ago

Verified e51c47b4

vulkan: Catch pipeline creation failure and print an error message (#11436)

jeffbolznv committed 1 year ago

Verified 2711d021

Parse https://ollama.com/library/ syntax (#11480)

ericcurtin committed 1 year ago

Verified f0d4b29e

ggerganov committed 1 year ago

Verified 81585779

ggml : add option to not print stack on abort (ggml/1081)

WilliamTambellini committed 1 year ago

Verified 1a0e87d2

ggml-cpu : fix ggml_graph_compute_thread did not terminate on abort. (ggml/1065)

issixx committed 1 year ago

Verified d2e518e9

embedding : enable --no-warmup option (#11475)

danbev committed 1 year ago

Verified b636228c

Older