 Eve
|
5c3d0f1824
ggml : IQ4_NL sgemm + Q4_0 AVX optimization (#9422)
|
vor 1 Jahr |
 Shane A
|
0aadac10c7
llama : support OLMoE (#9462)
|
vor 1 Jahr |
 CarryFun
|
95ca85168b
llama : support MiniCPM3 (#9322)
|
vor 1 Jahr |
 Vinesh Janarthanan
|
441b72b91f
main : option to disable context shift (#9484)
|
vor 1 Jahr |
 Georgi Gerganov
|
c4965a64f7
metal : handle zero-sized allocs (#9466)
|
vor 1 Jahr |
|
Georgi Gerganov
|
90a2fff0e7
flake.lock: Update (#9488)
|
vor 1 Jahr |
|
Georgi Gerganov
|
6262d13e0b
common : reimplement logging (#9418)
|
vor 1 Jahr |
 slaren
|
e6deac31f7
gguf-split : add basic checks (#9499)
|
vor 1 Jahr |
 Michael Podvitskiy
|
6988da94a2
cmake : correct order of sycl flags (#9497)
|
vor 1 Jahr |
 Csaba Kecskemeti
|
3c7989fd29
py : add "LLaMAForCausalLM" conversion support (#9485)
|
vor 1 Jahr |
 OSecret
|
d6b37c881f
readme : update tools list (#9475)
|
vor 1 Jahr |
|
Michael Podvitskiy
|
7596487beb
cmake : try to fix sycl+intel build (#9487)
|
vor 1 Jahr |
 Yuri Khrustalev
|
822b6322de
ggml : ggml_type_name return "NONE" for invalid values (#9458)
|
vor 1 Jahr |
 VoidIsVoid
|
dcdcee3a74
server: add data: [DONE] to /chat/completions stream response (#9459)
|
vor 1 Jahr |
|
Georgi Gerganov
|
1f4111e540
cmake : use list(APPEND ...) instead of set() + dedup linker (#9463)
|
vor 1 Jahr |
 Daniel Bevenius
|
befaf1197f
llama : make cell_id const in inp_s_mask block (#9470)
|
vor 1 Jahr |
 Xuan Son Nguyen
|
feff4aa846
server : add loading html page while model is loading (#9468)
|
vor 1 Jahr |
|
Georgi Gerganov
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
vor 1 Jahr |
 Gilad S.
|
bd35cb0ae3
feat: remove a sampler from a chain (#9445)
|
vor 1 Jahr |
 Mathijs Henquet
|
78203641fe
server : Add option to return token pieces in /tokenize endpoint (#9108)
|
vor 1 Jahr |
 Dou Xinpeng
|
e6b7801bd1
cann: Add host buffer type for Ascend NPU (#9406)
|
vor 1 Jahr |
 fengerhu1
|
e665744317
llava : fix the script error in MobileVLM README (#9054)
|
vor 1 Jahr |
|
Xuan Son Nguyen
|
d4c3c10fad
lora : raise error if lm_head is ignored (#9103)
|
vor 1 Jahr |
|
Michael Podvitskiy
|
2a825116b6
cmake : fix for builds without `GGML_CDEF_PUBLIC` (#9338)
|
vor 1 Jahr |
 Huang Qi
|
4dc4f5f14a
ci : update HIP SDK to 24.Q3 (ROCm 6.1) (#9329)
|
vor 1 Jahr |
 daminho
|
c837981bba
py : add Phi-1.5/Phi-2 tokenizer (#9361)
|
vor 1 Jahr |
 Trivikram Kamat
|
3c26a1644d
ci : bump actions/checkout to v4 (#9377)
|
vor 1 Jahr |
|
Michael Podvitskiy
|
ff76e18516
cmake : fixed the order of linking libraries for llama-quantize (#9450)
|
vor 1 Jahr |
 Molly Sophia
|
39f852f440
py : add special tokens in hf_converter for RWKV v6 (#9428)
|
vor 1 Jahr |
 Ahmad Tameem
|
2b00fa7997
riscv : modify Makefile and add a RISCV_VECT to print log info (#9442)
|
vor 1 Jahr |
