 Xuan Son Nguyen
|
96be8c3264
github : add cmd line field to bug report (#11090)
|
hai 1 ano |
 Georgi Gerganov
|
e6e7c75d94
server : fix extra BOS in infill endpoint (#11106)
|
hai 1 ano |
|
Xuan Son Nguyen
|
09186fabbe
llama : remove check flash_attn with lora (#11104)
|
hai 1 ano |
 Asghar Ghorbani
|
96a1dc27c3
llama : prevent system info string accumulation across calls (#11101)
|
hai 1 ano |
 Daniel Bevenius
|
6369f867a4
llama : rename missed batch params/vars to ubatch (#10059)
|
hai 1 ano |
|
Georgi Gerganov
|
47182dd03f
llama : update llama_model API names (#11063)
|
hai 1 ano |
|
Georgi Gerganov
|
3e6e7a6bc2
tokenize : escape the prompt (#11058)
|
hai 1 ano |
|
Georgi Gerganov
|
ae2f606bb5
mmap : fix fileno macro clash (#11076)
|
hai 1 ano |
|
Georgi Gerganov
|
727368c60f
llama : use LLAMA_TOKEN_NULL (#11062)
|
hai 1 ano |
|
Georgi Gerganov
|
5047dd3546
llama : use _impl suffix instead of _internal (#11060)
|
hai 1 ano |
 Johannes Gäßler
|
46e3556e01
CUDA: add BF16 support (#11093)
|
hai 1 ano |
 0cc4m
|
b56f079e28
Vulkan: Add device-specific blacklist for coopmat for the AMD proprietary driver (#11074)
|
hai 1 ano |
 fairydreaming
|
9394bbd484
llama : Add support for DeepSeek V3 (#11049)
|
hai 1 ano |
 matt23654
|
f922a9c542
[GGML][RPC] Support for models with non-512-aligned tensors over RPC. (#11047)
|
hai 1 ano |
 DAN™
|
46be942214
llama : add support for the cohere2 model architecture (#10900)
|
hai 1 ano |
|
Georgi Gerganov
|
78c6785175
sync : ggml
|
hai 1 ano |
|
Georgi Gerganov
|
5e3b08d606
ggml : do not install metal source when embed library (ggml/1054)
|
hai 1 ano |
|
Daniel Bevenius
|
db68c93b57
ggml : improve inputs log sched_print_assignments (ggml/1053)
|
hai 1 ano |
 Gilad S.
|
c31fc8b966
fix: Vulkan shader gen binary path (#11037)
|
hai 1 ano |
 Molly Sophia
|
4b0c638b9a
common : disable KV cache shifting automatically for unsupported models (#11053)
|
hai 1 ano |
|
Georgi Gerganov
|
e7da954ecc
metal : avoid uint (#11019)
|
hai 1 ano |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
hai 1 ano |
 Pierrick Hymbert
|
2f0ee84b9b
server: bench: minor fixes (#10765)
|
hai 1 ano |
|
Xuan Son Nguyen
|
0da5d86026
server : allow using LoRA adapters per-request (#10994)
|
hai 1 ano |
 Benson Wong
|
a45433ba20
readme : add llama-swap to infrastructure section (#11032)
|
hai 1 ano |
 Srihari-mcw
|
0827b2c1da
ggml : fixes for AVXVNNI instruction set with MSVC and Clang (#11027)
|
hai 1 ano |
|
Xuan Son Nguyen
|
45095a61bf
server : clean up built-in template detection (#11026)
|
hai 1 ano |
|
Xuan Son Nguyen
|
5896c65232
server : add OAI compat for /v1/completions (#10974)
|
hai 1 ano |
 ymcki
|
bc7b1f8632
convert : fix Llama-3_1-Nemotron-51B rope settings (#11008)
|
hai 1 ano |
 Peter
|
6e1531aca5
common, examples, ggml : fix MSYS2 GCC compiler errors and warnings when building with LLAMA_CURL=ON and GGML_OPENCL=ON (#11013)
|
hai 1 ano |
