ochafik/llama.cpp

Pull Requests Commits

json: print env vars in test

ochafik committed 2 years ago

60c75080

json: ensure py/js schema conv tested on ubuntu-focal-make

ochafik committed 2 years ago

cbb3e2f6

json: orange warnings when tests skipped

ochafik committed 2 years ago

ef3565fe

json: only attempt python & node schema conversion tests if their bins are present

ochafik committed 2 years ago

3c8a37a0

Corrected typo to wrong file (#6199)

semidark committed 2 years ago

Verified f372c49c

tests : disable system() calls (#6198)

ggerganov committed 2 years ago

Verified 924ce1dc

cuda : fix LLAMA_CUDA_F16 build (#6197)

slaren committed 2 years ago

Verified 03a8f8fa

ggml : same IQ4_NL quantization for CPU/CUDA/Metal (#6196)

ikawrakow committed 2 years ago

Verified cfd3be76

json-schema-to-grammar improvements (+ added to server) (#5978)

ochafik committed 2 years ago

Verified 5b7b0ac8

ci : fix indentation error (#6195)

Vaibhavs10 committed 2 years ago

Verified 1943c019

build : add mac pre-build binaries (#6182)

Vaibhavs10 committed 2 years ago

Verified 5e43ba87

Add ability to use Q5_0, Q5_1, and IQ4_NL for quantized K cache (#6183)

ikawrakow committed 2 years ago

Verified 76aa30a2

Add nvidia and amd backends (#6157)

AidanBeltonS committed 2 years ago

Verified c5b8595e

cuda : fix conflict with std::swap (#6186)

slaren committed 2 years ago

Verified 42e21c68

cuda : print the returned error when CUDA initialization fails (#6185)

slaren committed 2 years ago

Verified 1c51f98a

llava : update MobileVLM-README.md (#6180)

ZiangWu-77 committed 2 years ago

Verified f9c7ba34

llava : add MobileVLM_V2 backup (#6175)

ZiangWu-77 committed 2 years ago

Verified 272935b2

cuda : refactor to remove global resources (#6170)

slaren committed 2 years ago

Verified ccf58aa3

Server: version bump for httplib and json (#6169)

ngxson committed 2 years ago

Verified 91f8ad16

gitignore : ignore curl-related files

ggerganov committed 2 years ago

Verified 6b7e76d2

server : allow to override -ngl in tests (#6170)

ggerganov committed 2 years ago

Verified bc0baab2

Revert "llava : add a MobileVLM_V2-1.7B backup (#6152)"

ggerganov committed 2 years ago

Verified d795988d

llava : add a MobileVLM_V2-1.7B backup (#6152)

ZiangWu-77 committed 2 years ago

Verified f8c4e745

Server: Handle n_keep parameter in the request (#6174)

jkarthic committed 2 years ago

Verified 47cc7a7b

server tests : more pythonic process management; fix bare `except:` (#6146)

cebtenzzre committed 2 years ago

Verified bd60d82d

update readme sycl for new update (#6151)

NeoZhangJianyu committed 2 years ago

Verified 6c0b2877

increase igpu cluster limit (#6159)

abhilash1910 committed 2 years ago

Verified d26e8b66

Remove undeed header file. (#6158)

dranger003 committed 2 years ago

Verified d8b009a9

gguf-split: split and merge gguf per batch of tensors (#6135)

phymbert committed 2 years ago

Verified d0d5de42

common : disable repeat penalties by default (#6127)

ggerganov committed 2 years ago

Verified b80cf3b2

Older