Skip to content

Actions: VJHack/llama.cpp

Actions

Python check requirements.txt

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
python-check-requirements.yml
21 workflow runs
21 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

mtmd : Use RMS norm for InternVL 3 38B and 78B mmproj (#13459) Python check requirements.txt #22: Commit c104023 pushed by VJHack
3m 0s master
master
3m 0s
added llama_sampler_init Python check requirements.txt #21: Commit 38de7ec pushed by VJHack
2m 24s nsigma-sampling
nsigma-sampling
2m 24s
HIP: Switch to std::vector in rocblas version check (#11820) Python check requirements.txt #20: Commit e598697 pushed by VJHack
2m 34s master
master
2m 34s
resolve merge conflicts Python check requirements.txt #19: Commit 66cffa8 pushed by VJHack
2m 23s nsigma-sampling
nsigma-sampling
2m 23s
server : (UI) Improve messages bubble shape in RTL (#11220) Python check requirements.txt #18: Commit 504af20 pushed by VJHack
2m 25s master
master
2m 25s
llama: add support for QRWKV6 model architecture (#11001) Python check requirements.txt #17: Commit ee7136c pushed by VJHack
2m 25s master
master
2m 25s
ci : use actions from ggml-org (#11140) Python check requirements.txt #16: Commit f7cd133 pushed by VJHack
2m 34s master
master
2m 34s
llama-run : fix context size (#11094) Python check requirements.txt #15: Commit dc7cef9 pushed by VJHack
2m 32s master
master
2m 32s
CUDA: fix shared memory access condition for mmv (#10740) Python check requirements.txt #14: Commit 26a8406 pushed by VJHack
2m 33s master
master
2m 33s
convert : add custom attention mapping Python check requirements.txt #13: Commit c5ede38 pushed by VJHack
6m 4s master
master
6m 4s
ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_… Python check requirements.txt #12: Commit 0c39f44 pushed by VJHack
2m 31s master
master
2m 31s
Introduce llama-run (#10291) Python check requirements.txt #11: Commit 0cc6375 pushed by VJHack
2m 31s master
master
2m 31s
readme : update hot topics Python check requirements.txt #10: Commit ba6f62e pushed by VJHack
29m 4s master
master
29m 4s
generate token until context filled Python check requirements.txt #9: Commit b4bf5df pushed by VJHack
2m 56s server
server
2m 56s
llama : switch KQ multiplication to F32 precision by default (#10015) Python check requirements.txt #8: Commit 8841ce3 pushed by VJHack
2m 32s master
master
2m 32s
readme : update bindings list (#9918) Python check requirements.txt #7: Commit 3752217 pushed by VJHack
2m 57s master
master
2m 57s
cleanup pr Python check requirements.txt #6: Commit 2333101 pushed by VJHack
20m 42s oai_json_schema
oai_json_schema
20m 42s
[SYCL]set context default value to avoid memory issue, update guide (… Python check requirements.txt #5: Commit faf67b3 pushed by VJHack
2m 51s master
master
2m 51s
ggml : move common CPU backend impl to new header (#9509) Python check requirements.txt #4: Commit 23e0d70 pushed by VJHack
2m 39s master
master
2m 39s
added server example to --no-context-shift args Python check requirements.txt #3: Commit f5a2392 pushed by VJHack
2m 26s server-disable-context-shift
server-disable-context-shift
2m 26s
py : add "LLaMAForCausalLM" conversion support (#9485) Python check requirements.txt #2: Commit 3c7989f pushed by VJHack
2m 36s master
master
2m 36s