Skip to content
GitLab
Explore
Sign in
Tags
Tags give the ability to mark specific points in history as being important
b2311
9bf297a0
·
workflows : remove nocleanup arg for check-requirements.sh (#5826)
·
Mar 02, 2024
b2308
c29af7e2
·
llama : add StarCoder2 support (#5795)
·
Mar 01, 2024
b2306
c2224f00
·
ggml-vulkan: fix VULKAN_CHECK_RESULTS flag, which was previously broken (#5813)
·
Mar 01, 2024
b2304
f49a5356
·
common : fix flag `--logits-all` to `--all-logits` (#5805)
·
Mar 01, 2024
b2303
3ab8b3a9
·
llama : cleanup unused mmq flags (#5772)
·
Mar 01, 2024
b2302
9600d59e
·
unicode : switch to multimap based nfd_map (#5799)
·
Mar 01, 2024
b2301
5cb02b4a
·
server: allow to override threads server pool with --threads-http (#5794)
·
Mar 01, 2024
b2300
6ea0f010
·
ci : add Ubuntu 22 Vulkan CI run (#5789)
·
Mar 01, 2024
b2299
f105471e
·
server : fix newlines in help (#5785)
·
Mar 01, 2024
b2298
38d15216
·
[SYCL] Use batched mul_mat pathway (#5591)
·
Mar 01, 2024
b2297
052051d8
·
Server: normalize naming (#5779)
·
Feb 29, 2024
b2296
d5ab2975
·
llama : constified `llama_set_state_data`'s `src` (#5774)
·
Feb 29, 2024
b2294
317709b2
·
make portability_enumeration_ext apple only (#5757)
·
Feb 28, 2024
b2293
08c5ee87
·
llama : remove deprecated API (#5770)
·
Feb 28, 2024
b2291
8c0e8f4e
·
sync : ggml
·
Feb 28, 2024
b2288
a693bea1
·
server : hit Ctrl+C twice to exit (#5734)
·
Feb 28, 2024
b2287
adcb12a9
·
llama : fix non-quantization of expert gating tensors (#5754)
·
Feb 28, 2024
b2286
177628bf
·
llama : improve BERT tokenization (#5740)
·
Feb 28, 2024
b2284
efc72253
·
server : add "/chat/completions" alias for "/v1/...` (#5722)
·
Feb 28, 2024
b2283
7c4263d4
·
ggml : make i-quants work with super-blocks of 64 (CPU,Metal) (#5760)
·
Feb 28, 2024
Prev
1
…
20
21
22
23
24
25
26
27
28
…
99
Next