 apcameron
|
a6704643b6
ggml : add support for the RISCV architecture (#1616)
|
il y a 2 ans |
 Kerfuffle
|
0df7d63e5b
Include server in releases + other build system cleanups (#1610)
|
il y a 2 ans |
 Henri Vasserman
|
97c9b77c4f
Add documentation about CLBlast (#1604)
|
il y a 2 ans |
|
Henri Vasserman
|
0ecb1bbbeb
[CI] Fix openblas (#1613)
|
il y a 2 ans |
 Georgi Gerganov
|
93618031c7
ggml : add ggml_tensor_overhead()
|
il y a 2 ans |
|
Henri Vasserman
|
83c54e6da5
[CI] CLBlast: Fix directory name (#1606)
|
il y a 2 ans |
|
Georgi Gerganov
|
bdbda1b17a
ggml : sync ggml core (minor additions, e.g. ggml_get_tensor_by_name())
|
il y a 2 ans |
|
Kerfuffle
|
66874d4fbc
Some improvements to loading the session with --prompt-cache (#1550)
|
il y a 2 ans |
 Johannes Gäßler
|
1fcdcc28b1
cuda : performance optimizations (#1530)
|
il y a 2 ans |
|
Henri Vasserman
|
ac7876ac20
Update CLBlast to 1.6.0 (#1580)
|
il y a 2 ans |
 Evan Jones
|
c31bbe934b
readme : add docs for chat-persistent.sh (#1568)
|
il y a 2 ans |
 Senemu
|
1359b6aba5
chat-persistent.sh : use bracket expressions in grep (#1564)
|
il y a 2 ans |
 Maarten ter Huurne
|
7d873811f3
Fix handling of "invalid property" when creating OpenCL command queue (#1565)
|
il y a 2 ans |
 0cc4m
|
2e6cd4b025
OpenCL Token Generation Acceleration (#1459)
|
il y a 2 ans |
 Steward Garcia
|
7e4ea5beff
examples : add server example with REST API (#1443)
|
il y a 2 ans |
 Stefan Sydow
|
7780e4f479
make : .PHONY clean (#1553)
|
il y a 2 ans |
|
Georgi Gerganov
|
265db9834e
ggml : output 3d sizes in ggml_graph_dump_dot()
|
il y a 2 ans |
|
Georgi Gerganov
|
fab49c685e
ggml : update WASM SIMD
|
il y a 2 ans |
 Zenix
|
b8ee340abe
feature : support blis and other blas implementation (#1536)
|
il y a 2 ans |
|
Henri Vasserman
|
9ecb30f959
OpenCL: Fixes for older devices. (#1435)
|
il y a 2 ans |
 Juuso Alasuutari
|
29cf5596fe
llama : define magic numbers as integer constants (#1518) (#1520)
|
il y a 2 ans |
|
Georgi Gerganov
|
3de84b2606
ggml : add ggml_clamp() (#1539)
|
il y a 2 ans |
|
Johannes Gäßler
|
affc76edfd
cuda : loading models directly into VRAM, norm calculation on GPU, broadcasting for ggml_mul (#1483)
|
il y a 2 ans |
|
Georgi Gerganov
|
ea600071cb
Revert "feature : add blis and other BLAS implementation support (#1502)"
|
il y a 2 ans |
|
Zenix
|
07e9ace0f9
feature : add blis and other BLAS implementation support (#1502)
|
il y a 2 ans |
|
Georgi Gerganov
|
ec2e10c444
llama : add llama_init_backend() API (close #1527)
|
il y a 2 ans |
 DannyDaemonic
|
d2c59b8ba4
Fix for mingw (#1462)
|
il y a 2 ans |
 Maxime
|
503db28849
llama : fix name shadowing and C4146 (#1526)
|
il y a 2 ans |
|
Georgi Gerganov
|
8a203f9fa1
llama : fix compile warnings in llama_set_state_data()
|
il y a 2 ans |
|
Georgi Gerganov
|
4fd3e29297
ggml : fix scalar implementation of Q4_1 dot
|
il y a 2 ans |
