 Georgi Gerganov
|
973f328b1e
Merge pull request #10788 from ggerganov/gg/gguf-py-0.11.0
|
1 year ago |
|
Georgi Gerganov
|
fb18934a97
gguf-py : bump version to 0.11.0
|
1 year ago |
 Xuan Son Nguyen
|
235f6e14bf
server : (UI) add tok/s, get rid of completion.js (#10786)
|
1 year ago |
 qingy1337
|
1a31d0dc00
Update README.md (#10772)
|
1 year ago |
|
Xuan Son Nguyen
|
92f77a640f
ci : pin nodejs to 22.11.0 (#10779)
|
1 year ago |
 kallewoof
|
484d2f31ae
bug-fix: snprintf prints NULL in place of the last character (#10419)
|
1 year ago |
 CentricStorm
|
4b4d92b098
docs: fix server documentation formatting (#10776)
|
1 year ago |
 Gilad S.
|
43041d2eb3
ggml: load all backends from a user-provided search path (#10699)
|
1 year ago |
 Jeff Bolz
|
b685daf386
vulkan: request round-to-even for fp16 in im2col/rope_head (#10767)
|
1 year ago |
 Eve
|
dafae66cc2
vulkan: dynamic subgroup size for the remaining k quants (#10745)
|
1 year ago |
 Bartowski
|
ae4b922614
imatrix : Add imatrix to --no-context-shift (#10766)
|
1 year ago |
 Andreas Kieslinger
|
750cb3e246
CUDA: rename macros to avoid conflicts with WinAPI (#10736)
|
1 year ago |
 Yüg
|
a86ad841f1
server : add flag to disable the web-ui (#10762) (#10751)
|
1 year ago |
|
Jeff Bolz
|
a05e2afcc2
vulkan: disable spirv-opt for coopmat shaders (#10763)
|
1 year ago |
 Johannes Gäßler
|
26a8406ba9
CUDA: fix shared memory access condition for mmv (#10740)
|
1 year ago |
 Srihari-mcw
|
c37fb4cf62
Changes to CMakePresets.json to add ninja clang target on windows (#10668)
|
1 year ago |
|
Jeff Bolz
|
3d98b4cb22
vulkan: fix compile warnings (#10731)
|
1 year ago |
 Borislav Stanimirov
|
1a05004743
cmake : simplify msvc charsets (#10672)
|
1 year ago |
|
Xuan Son Nguyen
|
ce8784bdb1
server : fix format_infill (#10724)
|
1 year ago |
|
Xuan Son Nguyen
|
e52522b869
server : bring back info of final chunk in stream mode (#10722)
|
1 year ago |
 stduhpf
|
06d70147e6
Vulkan: fix NaN in tanh.comp with AMD proprietary driver on Windows (#10723)
|
1 year ago |
 Diego Devesa
|
43ed389a3f
llama : use cmake for swift build (#10525)
|
1 year ago |
|
Jeff Bolz
|
ecc93d0558
vulkan: compile a test shader in cmake to check for coopmat2 support (#10713)
|
1 year ago |
 Robert Collins
|
62e84d9848
llama : add 128k yarn context for Qwen (#10698)
|
1 year ago |
|
Xuan Son Nguyen
|
3573fa8e7b
server : (refactor) no more json in server_task input (#10691)
|
1 year ago |
|
Georgi Gerganov
|
d9c3ba2b77
ggml : disable iq4_nl interleave size 8 (#10709)
|
1 year ago |
|
Georgi Gerganov
|
ce4a7b8493
server : various fixes (#10704)
|
1 year ago |
 Djip007
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 year ago |
|
Georgi Gerganov
|
c2a16c0bdb
server : fix free of spec context and batch (#10651)
|
1 year ago |
 0cc4m
|
3df784b305
Vulkan: VK_KHR_cooperative_matrix support to speed up prompt processing (#10597)
|
1 year ago |
