 Georgi Gerganov
|
1f4111e540
cmake : use list(APPEND ...) instead of set() + dedup linker (#9463)
|
1 vuosi sitten |
 Daniel Bevenius
|
befaf1197f
llama : make cell_id const in inp_s_mask block (#9470)
|
1 vuosi sitten |
 Xuan Son Nguyen
|
feff4aa846
server : add loading html page while model is loading (#9468)
|
1 vuosi sitten |
|
Georgi Gerganov
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
1 vuosi sitten |
 Gilad S.
|
bd35cb0ae3
feat: remove a sampler from a chain (#9445)
|
1 vuosi sitten |
 Mathijs Henquet
|
78203641fe
server : Add option to return token pieces in /tokenize endpoint (#9108)
|
1 vuosi sitten |
 Dou Xinpeng
|
e6b7801bd1
cann: Add host buffer type for Ascend NPU (#9406)
|
1 vuosi sitten |
 fengerhu1
|
e665744317
llava : fix the script error in MobileVLM README (#9054)
|
1 vuosi sitten |
|
Xuan Son Nguyen
|
d4c3c10fad
lora : raise error if lm_head is ignored (#9103)
|
1 vuosi sitten |
 Michael Podvitskiy
|
2a825116b6
cmake : fix for builds without `GGML_CDEF_PUBLIC` (#9338)
|
1 vuosi sitten |
 Huang Qi
|
4dc4f5f14a
ci : update HIP SDK to 24.Q3 (ROCm 6.1) (#9329)
|
1 vuosi sitten |
 daminho
|
c837981bba
py : add Phi-1.5/Phi-2 tokenizer (#9361)
|
1 vuosi sitten |
 Trivikram Kamat
|
3c26a1644d
ci : bump actions/checkout to v4 (#9377)
|
1 vuosi sitten |
|
Michael Podvitskiy
|
ff76e18516
cmake : fixed the order of linking libraries for llama-quantize (#9450)
|
1 vuosi sitten |
 Molly Sophia
|
39f852f440
py : add special tokens in hf_converter for RWKV v6 (#9428)
|
1 vuosi sitten |
 Ahmad Tameem
|
2b00fa7997
riscv : modify Makefile and add a RISCV_VECT to print log info (#9442)
|
1 vuosi sitten |
|
Georgi Gerganov
|
d6a04f872d
ggml : hide ggml_object, ggml_cgraph, ggml_hash_set (#9408)
|
1 vuosi sitten |
 Neo Zhang Jianyu
|
c9c8575a1a
enhance run script to be easy to change the parameters (#9448)
|
1 vuosi sitten |
|
Xinpeng Dou
|
df4b7945ae
cann: Fix error when running a non-exist op (#9424)
|
1 vuosi sitten |
 Faisal Zaghloul
|
449ccfb6f5
Add Jais to list of supported models (#9439)
|
1 vuosi sitten |
 slaren
|
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
|
1 vuosi sitten |
 Pavel Zloi
|
8db003a19d
py : support converting local models (#7547)
|
1 vuosi sitten |
|
Xuan Son Nguyen
|
0996c5597f
llava : correct args for minicpmv-cli (#9429)
|
1 vuosi sitten |
|
Xuan Son Nguyen
|
5bb2c5dbd2
files : remove accidentally added `lora_test` submodule (#9430)
|
1 vuosi sitten |
 Farbod Bijary
|
67155ab7f5
feat: Implements retrying logic for downloading models using --model-url flag (#9255)
|
1 vuosi sitten |
 Johannes Gäßler
|
5af118efda
CUDA: fix --split-mode row race condition (#9413)
|
1 vuosi sitten |
|
Georgi Gerganov
|
d2b496bff4
batched-bench : remove unused code (#9305)
|
1 vuosi sitten |
 R0CKSTAR
|
b34e023480
musa: remove Clang builtins mapping (#9421)
|
1 vuosi sitten |
 Alberto Cabrera Pérez
|
51b6038636
sycl : update support conditions (#9394)
|
1 vuosi sitten |
|
Georgi Gerganov
|
cb9c933eb2
flake.lock: Update (#9360)
|
1 vuosi sitten |
