ggerganov/llama.cpp

Pull Requests Commits

safer jinja `llama_chat_templates` struct

ngxson committed 227 days ago

c9e7cbb0

minja: fix vigogne (https://github.com/google/minja/pull/22)

ochafik committed 229 days ago

cc503564

Disable jinja test that has a cryptic windows failure

ochafik committed 229 days ago

e3c475cd

Add missing optional include to server.cpp

ochafik committed 229 days ago

0e74c9da

Rm unused optional include

ochafik committed 229 days ago

fc60802b

Fix copy elision warning

ochafik committed 229 days ago

5074e6fe

Flush stdout in chat template before potential crash

ochafik committed 229 days ago

33322e82

Forward decl minja::chat_template to avoid eager json dep

ochafik committed 229 days ago

e63520f3

Normalize newlines in test-chat-templates for windows tests

ochafik committed 230 days ago

ee1e10e2

Revert LLAMA_CHATML_TEMPLATE refactor

ochafik committed 230 days ago

d5fa351a

Attempt to fix linkage of LLAMA_CHATML_TEMPLATE

ochafik committed 230 days ago

81c0d437

Merge remote-tracking branch 'origin/master' into jinja

ochafik committed 230 days ago

40db7896

Refactor common_chat_* functions to accept minja template + use_jinja option

ochafik committed 230 days ago

b75d0622

llama.android: add field formatChat to control whether to parse special tokens when send message (#11270)

codezjx committed 230 days ago

Verified 3edfa7d3

rpc : early register backend devices (#11262)

rgerganov committed 230 days ago

Verified 667d7284

vocab : fix double-eos check (#11273)

ggerganov committed 231 days ago

Verified a133566d

llama : fix deprecation message: vocabable -> vocab (#11269)

dwrensha committed 231 days ago

Verified 960ec652

README : added kalavai to infrastructure list (#11216)

musoles committed 231 days ago

Verified 7a689c41

vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl (#11166)

jeffbolznv committed 231 days ago

Verified bd38ddea

vulkan: optimize coopmat2 q4_k/q5_k dequant functions. (#11206)

jeffbolznv committed 231 days ago

Verified 466300fe

vulkan: optimize coopmat2 q2_k dequant function (#11130)

jeffbolznv committed 231 days ago

Verified 206bc534

llama : add internlm3 support (#11233)

RunningLeon committed 231 days ago

Verified 4dbc8b9c

CUDA: backwards pass for misc. ops, add tests (#11257)

JohannesGaessler committed 231 days ago

Verified 9c8dcefe

llama : add `llama_model_load_from_splits` (#11255)

ngxson committed 231 days ago

Verified 681149ce

ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (#11227)

fj-y-saito committed 231 days ago

Verified c67cc983

vulkan: scale caching for k quants + misc fixes (#11081)

netrunnereve committed 232 days ago

Verified adc5dd92

ci : use -no-cnv in gguf-split tests (#11254)

ggerganov committed 232 days ago

Verified f11cfdfd

fix: ggml: fix vulkan-shaders-gen build (#10448)

sparkleholic committed 232 days ago

Verified 1d850433

RoPE: fix back, CUDA support for back + noncont. (#11240)

JohannesGaessler committed 232 days ago

Verified 432df2d5

examples : add embd_to_audio to tts-outetts.py [no ci] (#11235)

danbev committed 233 days ago

Verified 0ccd7f3e

Older