ochafik/llama.cpp

Pull Requests Commits
llama : add support for Deepseek-R1-Qwen distill model (#11310)
ngxson committed 1 year ago
Verified ec7f3ac9
cont : fix whitespaces (#11305)
ggerganov committed 1 year ago
Verified ef6dada6
llama : re-add LLM_ARCH_PHIMOE (#11305)
KyleBruene committed 1 year ago
Verified ae3c1db2
tests : increase timeout when sanitizers are enabled (#11300)
ggerganov committed 1 year ago
Verified 92bc4939
simple-chat : fix BOS being added to each message (#11278)
ggerganov committed 1 year ago
Verified b9daaffe
SYCL: Introducing memory host pool (#11251)
s-Nick committed 1 year ago
Verified 99487b57
agent: add --greedy, --top-p, --top-k options
ochafik committed 1 year ago
0401a83b
Merge branch 'jinja' into tool-call
ochafik committed 1 year ago
c207fdcd
minja: fix vigogne (https://github.com/google/minja/pull/22)
ochafik committed 1 year ago
cc503564
Disable jinja test that has a cryptic windows failure
ochafik committed 1 year ago
e3c475cd
Merge branch 'jinja' into tool-call
ochafik committed 1 year ago
d6f058da
Adding linenoise.cpp to llama-run (#11252)
ericcurtin committed 1 year ago
Verified a1649cc1
cmake : add sanitizer flags for llama.cpp (#11279)
ggerganov committed 1 year ago
Verified 4dd34ff8
server : implement cancellable request (#11285)
ngxson committed 1 year ago
Verified f30f0992
Add missing optional include to server.cpp
ochafik committed 1 year ago
0e74c9da
Rm unused optional include
ochafik committed 1 year ago
fc60802b
Merge branch 'jinja' into tool-call
ochafik committed 1 year ago
76893f58
scripts : restore hf.sh (#11288)
ggerganov committed 1 year ago
Verified f26c8741
Fix copy elision warning
ochafik committed 1 year ago
5074e6fe
Flush stdout in chat template before potential crash
ochafik committed 1 year ago
33322e82
Forward decl minja::chat_template to avoid eager json dep
ochafik committed 1 year ago
e63520f3
tts : add guide tokens support (#11186)
LostRuins committed 1 year ago
Verified 6390a998
vulkan: fix coopmat2 flash attention for non-contiguous inputs (#11281)
jeffbolznv committed 1 year ago
Verified 44e18ef9
Normalize newlines in test-chat-templates for windows tests
ochafik committed 1 year ago
ee1e10e2
tools: run tool call slow tests when SLOW_TESTS=1 (+ prefetch models)
ochafik committed 1 year ago
acf7c240
tools: greedy sampling in tests
ochafik committed 1 year ago
259d9e45
Fix fetch_server_test_models.py (avoid conv trap)
ochafik committed 1 year ago
2ceabee0
Merge branch 'jinja' into tool-call
ochafik committed 1 year ago
045edd1d
Revert LLAMA_CHATML_TEMPLATE refactor
ochafik committed 1 year ago
d5fa351a
Merge branch 'jinja' into tool-call
ochafik committed 1 year ago
138a4ba8
Terms Of Use Privacy Policy Refund Policy Impressum