root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity
All Workflows build.yml close-issue.yml docker.yml editorconfig.yml gguf-publish.yml labeler.yml python-check-requirements.yml python-lint.yml python-type-check.yml server.yml
Actor
All actors root
Status
All status success failure waiting running
server : fix missing model id in /model endpoint (#10957)
#1567:Scheduled
master
2024-12-24 00:42:32 +00:00
0s
vulkan: build fixes for 32b (#10927)
#1551:Scheduled
master
2024-12-24 00:42:32 +00:00
0s
convert : add BertForMaskedLM (#10919)
#1549:Scheduled
master
2024-12-23 00:42:32 +00:00
0s
SYCL: Migrate away from deprecated ggml_tensor->backend (#10840)
#1544:Scheduled
master
2024-12-22 00:42:32 +00:00
0s
clip : disable GPU support (#10896)
#1535:Scheduled
master
2024-12-21 00:42:32 +00:00
0s
ggml : fix arm build (#10890)
#1526:Scheduled
master
2024-12-20 00:42:32 +00:00
0s
Use model->gguf_kv for loading the template instead of using the C API. (#10868)
#1511:Scheduled
master
2024-12-19 00:42:32 +00:00
0s
rwkv6: add wkv6 support for Vulkan backend (#10829)
#1498:Scheduled
master
2024-12-18 00:42:32 +00:00
0s
llava : Allow locally downloaded models for QwenVL (#10833)
#1494:Scheduled
master
2024-12-17 00:42:32 +00:00
0s
nix: allow to override rocm gpu targets (#10794)
#1481:Scheduled
master
2024-12-16 00:42:32 +00:00
0s
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
#1474:Scheduled
master
2024-12-15 00:42:32 +00:00
0s
contrib : add ngxson as codeowner (#10804)
#1469:Scheduled
master
2024-12-14 00:42:49 +00:00
0s
server : (UI) add tok/s, get rid of completion.js (#10786)
#1403:Scheduled
master
2024-12-13 00:42:49 +00:00
0s
vulkan: dynamic subgroup size for the remaining k quants (#10745)
#1398:Scheduled
master
2024-12-12 00:42:49 +00:00
0s
CUDA: fix shared memory access condition for mmv (#10740)
#1392:Scheduled
master
2024-12-11 00:42:49 +00:00
0s
Vulkan: fix NaN in tanh.comp with AMD proprietary driver on Windows (#10723)
#1386:Scheduled
master
2024-12-10 00:42:49 +00:00
0s
ggml : disable iq4_nl interleave size 8 (#10709)
#1378:Scheduled
master
2024-12-09 00:42:49 +00:00
0s
common : bring back --no-warmup to server (#10686)
#1368:Scheduled
master
2024-12-08 00:42:49 +00:00
0s
sync : ggml
#1357:Scheduled
master
2024-12-07 00:42:49 +00:00
0s
ggml : add predefined list of CPU backend variants to build (#10626)
#1352:Scheduled
master
2024-12-06 00:42:49 +00:00
0s
clip : add sycl support (#10574)
#1344:Scheduled
master
2024-12-05 00:42:49 +00:00
0s
llama : add enum for built-in chat templates (#10623)
#1340:Scheduled
master
2024-12-04 00:42:49 +00:00
0s
Add `mistral-v1`, `mistral-v3`, `mistral-v3-tekken` and `mistral-v7` chat template types (#10572)
#1332:Scheduled
master
2024-12-03 00:42:49 +00:00
0s
ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_q4_0_4x4_q8_0() (#10567)
#1330:Scheduled
master
2024-12-02 00:42:49 +00:00
0s
ggml : move AMX to the CPU backend (#10570)
#1327:Scheduled
master
2024-12-01 00:42:49 +00:00
0s
ggml : remove redundant copyright notice + update authors
#1321:Scheduled
master
2024-11-30 00:42:49 +00:00
0s
Add some minimal optimizations for CDNA (#10498)
#1311:Scheduled
master
2024-11-29 00:42:49 +00:00
0s
Add OLMo 2 model in docs (#10530)
#1309:Scheduled
master
2024-11-28 00:42:49 +00:00
0s
server : add more information about error (#10455)
#1272:Scheduled
master
2024-11-27 00:42:49 +00:00
0s
flake.lock: Update (#10470)
#1240:Scheduled
master
2024-11-26 00:42:49 +00:00
0s