 Xuan Son Nguyen
|
26a39bbd6b
Add MiniCPM, Deepseek V2 chat template + clean up `llama_chat_apply_template_internal` (#8172)
|
1 year ago |
 Sigbjørn Skjæret
|
38373cfbab
Add SPM infill support (#8016)
|
1 year ago |
 slaren
|
b851b3fba0
cmake : allow user to override default options (#8178)
|
1 year ago |
 Olivier Chafik
|
139cc621e9
`json`: restore default additionalProperties to false, fix some pattern escapes (#8180)
|
1 year ago |
 pculliton
|
e57dc62057
llama: Add support for Gemma2ForCausalLM (#8156)
|
1 year ago |
|
Xuan Son Nguyen
|
a27aa50ab7
Add missing items in makefile (#8177)
|
1 year ago |
|
Olivier Chafik
|
cb0b06a8a6
`json`: update grammars/README w/ examples & note about additionalProperties (#8132)
|
1 year ago |
 loonerin
|
558f44bf83
CI: fix release build (Ubuntu+Mac) (#8170)
|
1 year ago |
|
slaren
|
8172ee9da9
cmake : fix deprecated option names not working (#8171)
|
1 year ago |
|
Xuan Son Nguyen
|
16791b8f0b
Add chatml fallback for cpp `llama_chat_apply_template` (#8160)
|
1 year ago |
 Georgi Gerganov
|
ab3679112d
flake.lock: Update (#8071)
|
1 year ago |
 jukofyork
|
97877eb10b
Control vector loading fixes (#8137)
|
1 year ago |
 Raj Hammeer Singh Hada
|
387952651a
Delete examples/llama.android/llama/CMakeLists.txt (#8165)
|
1 year ago |
|
Sigbjørn Skjæret
|
6030c61281
Add Qwen2MoE 57B-A14B model identifier (#8158)
|
1 year ago |
 Johannes Gäßler
|
85a267daaa
CUDA: fix MMQ stream-k for --split-mode row (#8167)
|
1 year ago |
 kustaaya
|
f675b20a3b
Added support for Viking pre-tokenizer (#8135)
|
1 year ago |
|
Sigbjørn Skjæret
|
911e35bb8b
llama : fix CodeLlama FIM token checks (#8144)
|
1 year ago |
|
Raj Hammeer Singh Hada
|
ac146628e4
Fix llama-android.cpp for error - "common/common.h not found" (#8145)
|
1 year ago |
 Daniel Bevenius
|
9b31a40c6d
clip : suppress unused variable warnings (#8105)
|
1 year ago |
|
Georgi Gerganov
|
c70d117c37
scripts : fix filename sync
|
1 year ago |
|
slaren
|
ae5d0f4b89
ci : publish new docker images only when the files change (#8142)
|
1 year ago |
|
slaren
|
31ec3993f6
ggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CUDA_FORCE_CUBLAS (cmake) (#8140)
|
1 year ago |
|
slaren
|
c7ab7b612c
make : fix missing -O3 (#8143)
|
1 year ago |
|
Georgi Gerganov
|
f2d48fffde
sync : ggml
|
1 year ago |
|
Georgi Gerganov
|
4713bf3093
authors : regen
|
1 year ago |
|
Georgi Gerganov
|
0e814dfc42
devops : remove clblast + LLAMA_CUDA -> GGML_CUDA (#8139)
|
1 year ago |
|
Georgi Gerganov
|
a95631ee97
readme : update API notes
|
1 year ago |
|
Georgi Gerganov
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
 Isaac McFadyen
|
8854044561
Clarify default MMQ for CUDA and LLAMA_CUDA_FORCE_MMQ flag (#8115)
|
1 year ago |
|
Johannes Gäßler
|
c8771ab5f8
CUDA: fix misaligned shared memory read (#8123)
|
1 year ago |
