 0cc4m
|
2e6cd4b025
OpenCL Token Generation Acceleration (#1459)
|
%!s(int64=2) %!d(string=hai) anos |
 Steward Garcia
|
7e4ea5beff
examples : add server example with REST API (#1443)
|
%!s(int64=2) %!d(string=hai) anos |
 Stefan Sydow
|
7780e4f479
make : .PHONY clean (#1553)
|
%!s(int64=2) %!d(string=hai) anos |
 Georgi Gerganov
|
265db9834e
ggml : output 3d sizes in ggml_graph_dump_dot()
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
fab49c685e
ggml : update WASM SIMD
|
%!s(int64=2) %!d(string=hai) anos |
 Zenix
|
b8ee340abe
feature : support blis and other blas implementation (#1536)
|
%!s(int64=2) %!d(string=hai) anos |
 Henri Vasserman
|
9ecb30f959
OpenCL: Fixes for older devices. (#1435)
|
%!s(int64=2) %!d(string=hai) anos |
 Juuso Alasuutari
|
29cf5596fe
llama : define magic numbers as integer constants (#1518) (#1520)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
3de84b2606
ggml : add ggml_clamp() (#1539)
|
%!s(int64=2) %!d(string=hai) anos |
 Johannes Gäßler
|
affc76edfd
cuda : loading models directly into VRAM, norm calculation on GPU, broadcasting for ggml_mul (#1483)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
ea600071cb
Revert "feature : add blis and other BLAS implementation support (#1502)"
|
%!s(int64=2) %!d(string=hai) anos |
|
Zenix
|
07e9ace0f9
feature : add blis and other BLAS implementation support (#1502)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
ec2e10c444
llama : add llama_init_backend() API (close #1527)
|
%!s(int64=2) %!d(string=hai) anos |
 DannyDaemonic
|
d2c59b8ba4
Fix for mingw (#1462)
|
%!s(int64=2) %!d(string=hai) anos |
 Maxime
|
503db28849
llama : fix name shadowing and C4146 (#1526)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
8a203f9fa1
llama : fix compile warnings in llama_set_state_data()
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
4fd3e29297
ggml : fix scalar implementation of Q4_1 dot
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
2d5db48371
ggml : use F16 instead of F32 in Q4_0, Q4_1, Q8_0 (#1508)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
6986c7835a
tests : add missing header
|
%!s(int64=2) %!d(string=hai) anos |
 Evan Jones
|
943e6081cc
examples : add persistent chat (#1495)
|
%!s(int64=2) %!d(string=hai) anos |
 Jason McCartney
|
7694b52b9a
main : make reverse prompt option act as a stop token in non-interactive mode (#1032)
|
%!s(int64=2) %!d(string=hai) anos |
 David Kennedy
|
79e3efb0e9
readme : adds WizardLM to the list of supported models (#1485)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
4b7e245adf
minor : fix compile warnings
|
%!s(int64=2) %!d(string=hai) anos |
 Erik Scholz
|
5ea4339273
make kv_f16 the default for api users (#1517)
|
%!s(int64=2) %!d(string=hai) anos |
|
DannyDaemonic
|
ee9654138a
Fixes #1511 lambda issue for w64devkit (mingw) (#1513)
|
%!s(int64=2) %!d(string=hai) anos |
 Stephan Walter
|
dc271c52ed
Remove unused n_parts parameter (#1509)
|
%!s(int64=2) %!d(string=hai) anos |
 rankaiyx
|
c238b5873a
benchmark-matmul: Print the average of the test results (#1490)
|
%!s(int64=2) %!d(string=hai) anos |
 Tom Jobbins
|
2b2646931b
convert.py: Support models which are stored in a single pytorch_model.bin (#1469)
|
%!s(int64=2) %!d(string=hai) anos |
 Ilya Kurdyukov
|
42627421ec
~7% faster Q5_1 AVX2 code (#1477)
|
%!s(int64=2) %!d(string=hai) anos |
 András Salamon
|
9560655409
define default model path once, sync path with readme (#1366)
|
%!s(int64=2) %!d(string=hai) anos |
