 Engininja2
|
cd4fddb29f
cuda : fix 2-bit quants on amd hip (#5105)
|
2 years ago |
 Michael Hueschen
|
c9b316c78f
nix-shell: use addToSearchPath
|
2 years ago |
|
Michael Hueschen
|
bf63d695b8
nix: add cc to devShell LD_LIBRARY_PATH
|
2 years ago |
 slaren
|
1387ea2117
llama : pre-allocate input tensors in a separate buffer (#5100)
|
2 years ago |
 Georgi Gerganov
|
26d607608d
metal : disable support for MUL_MAT F32 x F16
|
2 years ago |
 Kawrakow
|
44879ee885
Additional KL-divergence statistics (#5081)
|
2 years ago |
 Johannes Gäßler
|
9ecdd12e95
CUDA: more info when no device code (#5088)
|
2 years ago |
|
Georgi Gerganov
|
89758723c7
minor : clean-up some warnings and style (#5094)
|
2 years ago |
 Xuan Son Nguyen
|
2bed4aa3f3
devops : add intel oneapi dockerfile (#5068)
|
2 years ago |
 Michael Coppola
|
125d03a503
llama.vim : added api key support (#5090)
|
2 years ago |
|
slaren
|
011e8ec577
llama : fix not enough space in buffer with Qwen (#5086)
|
2 years ago |
|
Kawrakow
|
6f9939d119
KL-divergence (#5076)
|
2 years ago |
 Reinforce-II
|
780e24a22e
ggml : parallelize FP32 conversion when using BLAS (#5045)
|
2 years ago |
 XiaotaoChen
|
3ce7e8f8e7
llava : MobileVLM support (#4954)
|
2 years ago |
 Someone Serge
|
b2d80e105a
flake.nix: add a comment about flakes vs nix
|
2 years ago |
|
Someone Serge
|
28603cd283
nix: add a comment on the many nixpkgs-with-cuda instances
|
2 years ago |
|
Someone Serge
|
5e97ec91ae
nix: add a comment about makeScope
|
2 years ago |
|
Someone Serge
|
7251870780
nix: refactor the cleanSource rules
|
2 years ago |
|
Someone Serge
|
fe8b3c0d4b
workflows: nix-ci: drop the redundant "paths" filter
|
2 years ago |
|
Someone Serge
|
f4dd059259
workflows: nix-build-aarch64: rate limit
|
2 years ago |
|
Someone Serge
|
f7276f7500
workflows: nix-ci: rebuild on flake.lock updates
|
2 years ago |
|
Kawrakow
|
15bceec2d7
imatrix : keep intermediate imatrix results (#5077)
|
2 years ago |
 compilade
|
d6bd4d46dd
llama : support StableLM 2 1.6B (#5052)
|
2 years ago |
 Daniel Bevenius
|
152d9d05e0
finetune : print sample-start/include-sample-start (#5072)
|
2 years ago |
|
Kawrakow
|
66d575c45c
llama : add Q3_K_XS (#5060)
|
2 years ago |
 bobqianic
|
57744932c6
ci : fix Windows CI by updating Intel SDE version (#5053)
|
2 years ago |
 Shijie
|
3466c6ebcf
llama : add more qwen2 models (#5071)
|
2 years ago |
 iSma
|
504dc37be8
Revert LLAMA_NATIVE to OFF in flake.nix (#5066)
|
2 years ago |
 kuronekosaiko
|
05490fad7f
add safetensors support to convert-lora-to-ggml.py (#5062)
|
2 years ago |
|
bobqianic
|
6c5629d4d2
add `#include <string>` to unicode.h (#5051)
|
2 years ago |
