 chiranko
|
5d55b0cd82
readme : add CodeShell models to the supported models list (#5330)
|
%!s(int64=2) %!d(string=hai) anos |
 AidanBeltonS
|
4833ac209d
[SYCL] Fix cpy with dims of 3 (#5289)
|
%!s(int64=2) %!d(string=hai) anos |
 github-actions[bot]
|
9392ebd49e
flake.lock: Update
|
%!s(int64=2) %!d(string=hai) anos |
 Kawrakow
|
5ed26e1fc9
Adding some imatrix tools (#5302)
|
%!s(int64=2) %!d(string=hai) anos |
 Welby Seely
|
277fad30c6
cmake : use set() for LLAMA_WIN_VER (#5298)
|
%!s(int64=2) %!d(string=hai) anos |
 Johannes Gäßler
|
3c0d25c475
make: add nvcc info print (#5310)
|
%!s(int64=2) %!d(string=hai) anos |
|
Johannes Gäßler
|
3cc5ed353c
make: fix nvcc optimization flags for host code (#5309)
|
%!s(int64=2) %!d(string=hai) anos |
 Martin Schwaighofer
|
60ecf099ed
add Vulkan support to Nix flake
|
%!s(int64=2) %!d(string=hai) anos |
 0cc4m
|
e920ed393d
Vulkan Intel Fixes, Optimizations and Debugging Flags (#5301)
|
%!s(int64=2) %!d(string=hai) anos |
 Michael Klimenko
|
52bb63c708
refactor : switch to emplace_back to avoid extra object (#5291)
|
%!s(int64=2) %!d(string=hai) anos |
 Jared Van Bortel
|
1ec3332ade
YaRN : store rope scaling type as int32_t in memory (#5285)
|
%!s(int64=2) %!d(string=hai) anos |
 BADR
|
6a66c5071a
readme : add tenere in the ui tools list (#5284)
|
%!s(int64=2) %!d(string=hai) anos |
|
AidanBeltonS
|
a305dba8ff
Fix im2col with 32fp (#5286)
|
%!s(int64=2) %!d(string=hai) anos |
 kalomaze
|
191221178f
perplexity : fix KL divergence calculations on Windows (#5273)
|
%!s(int64=2) %!d(string=hai) anos |
 Georgi Gerganov
|
e437b37fd0
scripts : parse wtype in server-llm.sh (#5167)
|
%!s(int64=2) %!d(string=hai) anos |
 Mirror Azure
|
2d40085c26
py : add check for '.attn.masked_bias' layers to GPT2model (#5281)
|
%!s(int64=2) %!d(string=hai) anos |
|
AidanBeltonS
|
b05102fe8c
Tidy ggml-sycl (#5261)
|
%!s(int64=2) %!d(string=hai) anos |
 Xuan Son Nguyen
|
6b91b1e0a9
docker : add build for SYCL, Vulkan + update readme (#5228)
|
%!s(int64=2) %!d(string=hai) anos |
 Meng, Hengyu
|
e805f0fa99
[SYCL] get MAX_MEM_ALLOC from device property (#5270)
|
%!s(int64=2) %!d(string=hai) anos |
 Neo Zhang Jianyu
|
af3ba5d946
[SYCL] update guide of SYCL backend (#5254)
|
%!s(int64=2) %!d(string=hai) anos |
 Ian Bull
|
e1e721094d
llama : fix memory leak in llama_batch_free (#5252)
|
%!s(int64=2) %!d(string=hai) anos |
|
Neo Zhang Jianyu
|
128dcbd3c9
add --no-mmap in llama-bench (#5257)
|
%!s(int64=2) %!d(string=hai) anos |
|
0cc4m
|
4d0924a890
Vulkan Phi Fix for AMD Proprietary Drivers (#5260)
|
%!s(int64=2) %!d(string=hai) anos |
 slaren
|
8ca511cade
cuda : fix LLAMA_CUDA_F16 (#5262)
|
%!s(int64=2) %!d(string=hai) anos |
 Ali Nehzat
|
d71ac90985
make : generate .a library for static linking (#5205)
|
%!s(int64=2) %!d(string=hai) anos |
 Guoteng
|
ce32060198
llama : support InternLM2 (#5184)
|
%!s(int64=2) %!d(string=hai) anos |
 Eve
|
1cfb5372cf
Fix broken Vulkan Cmake (properly) (#5230)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
d3bac7d584
llama : reorder build_orion() at correct place (#5118)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
5cb04dbc16
llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
efb7bdbbd0
metal : add im2col F32 dst support (#5132)
|
%!s(int64=2) %!d(string=hai) anos |
