Skip to content

Actions: ggerganov/llama.cpp

Actions

Code Coverage

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
11,934 workflow runs
11,934 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[SYCL] remove global variables Code Coverage #13238: Pull request #7710 synchronize by airMeng
June 15, 2024 02:12 20m 31s sycl-remove-global-variables
sycl-remove-global-variables
June 15, 2024 02:12 20m 31s
use macro for group_size and remove cuda-related Code Coverage #13237: Commit 28eaafc pushed by airMeng
June 15, 2024 02:12 5m 18s sycl-remove-global-variables
sycl-remove-global-variables
June 15, 2024 02:12 5m 18s
Add support for BitnetForCausalLM (new model / new datatype) Code Coverage #13236: Pull request #7931 synchronize by Eddie-Wang1120
June 15, 2024 02:10 18m 23s Eddie-Wang1120:bitnet
Eddie-Wang1120:bitnet
June 15, 2024 02:10 18m 23s
Tokenizer BPE fixes Code Coverage #13235: Pull request #7530 synchronize by jaime-m-p
June 15, 2024 02:03 4m 23s jaime-m-p:tokenizer-bpe-fixes
jaime-m-p:tokenizer-bpe-fixes
June 15, 2024 02:03 4m 23s
Tokenizer BPE fixes Code Coverage #13234: Pull request #7530 synchronize by jaime-m-p
June 15, 2024 01:36 2m 0s jaime-m-p:tokenizer-bpe-fixes
jaime-m-p:tokenizer-bpe-fixes
June 15, 2024 01:36 2m 0s
Allow pooled embeddings on any model Code Coverage #13232: Pull request #7477 synchronize by iamlemec
June 14, 2024 18:34 1m 59s iamlemec:append-pooling
iamlemec:append-pooling
June 14, 2024 18:34 1m 59s
ci : fix macos x86 build (#7940) Code Coverage #13231: Commit f8ec887 pushed by ggerganov
June 14, 2024 17:28 13m 51s master
master
June 14, 2024 17:28 13m 51s
AVX IQ Quants Code Coverage #13230: Pull request #7845 synchronize by netrunnereve
June 14, 2024 16:51 40m 26s avx_iq
avx_iq
June 14, 2024 16:51 40m 26s
CUDA: faster q2_K, q3_K MMQ + int8 tensor cores (#7921) Code Coverage #13229: Commit 76d66ee pushed by JohannesGaessler
June 14, 2024 16:41 5m 25s master
master
June 14, 2024 16:41 5m 25s
Fix macos x86 build Code Coverage #13228: Pull request #7940 opened by olexiyb
June 14, 2024 15:58 15m 54s Sanctum-AI:fix-macos-x86-build
Sanctum-AI:fix-macos-x86-build
June 14, 2024 15:58 15m 54s
CUDA: faster q2_K, q3_K MMQ + int8 tensor cores Code Coverage #13227: Pull request #7921 synchronize by JohannesGaessler
June 14, 2024 15:51 13m 48s JohannesGaessler:cuda-ptx-mma-17
JohannesGaessler:cuda-ptx-mma-17
June 14, 2024 15:51 13m 48s
examples: refine tensor_sum_elements(tensor dump) in examples/benchmark/benchmark-matmult.cpp Code Coverage #13226: Pull request #7844 synchronize by zhouwg
June 14, 2024 15:19 9m 10s zhouwg:refinetensordump
zhouwg:refinetensordump
June 14, 2024 15:19 9m 10s
examples: refine tensor_sum_elements(tensor dump) in examples/benchmark/benchmark-matmult.cpp Code Coverage #13225: Pull request #7844 synchronize by zhouwg
June 14, 2024 15:04 14m 31s zhouwg:refinetensordump
zhouwg:refinetensordump
June 14, 2024 15:04 14m 31s
CUDA: faster q2_K, q3_K MMQ + int8 tensor cores Code Coverage #13224: Pull request #7921 synchronize by JohannesGaessler
June 14, 2024 14:28 48m 47s JohannesGaessler:cuda-ptx-mma-17
JohannesGaessler:cuda-ptx-mma-17
June 14, 2024 14:28 48m 47s
gguf-dump.py: add --markdown dump output Code Coverage #13223: Pull request #7853 synchronize by mofosyne
June 14, 2024 14:15 49m 24s mofosyne:gguf-dump-markdown
mofosyne:gguf-dump-markdown
June 14, 2024 14:15 49m 24s
metal : utilize max shared memory for mul_mat_id (#7935) Code Coverage #13222: Commit 66ef1ce pushed by ggerganov
June 14, 2024 14:14 17m 41s master
master
June 14, 2024 14:14 17m 41s
Merge pull request #7920 from ggerganov/codeplay/revert-host-alloc Code Coverage #13221: Commit ff076b8 pushed by joeatodd
June 14, 2024 14:10 19m 35s codeplay/sycl-main
codeplay/sycl-main
June 14, 2024 14:10 19m 35s
Merge pull request #7919 from ggerganov/codeplay/unify-rope-sycl Code Coverage #13220: Commit b2c8c83 pushed by joeatodd
June 14, 2024 14:08 9m 56s codeplay/sycl-main
codeplay/sycl-main
June 14, 2024 14:08 9m 56s
gguf-dump.py: add --markdown dump output Code Coverage #13219: Pull request #7853 synchronize by mofosyne
June 14, 2024 14:05 3m 33s mofosyne:gguf-dump-markdown
mofosyne:gguf-dump-markdown
June 14, 2024 14:05 3m 33s
llama-bench : fix RPC indication (#7936) Code Coverage #13218: Commit e65bbf6 pushed by rgerganov
June 14, 2024 13:47 5m 50s master
master
June 14, 2024 13:47 5m 50s
sycl-exp : unify rope neox/norm Code Coverage #13217: Pull request #7919 synchronize by joeatodd
June 14, 2024 12:30 10m 30s codeplay/unify-rope-sycl
codeplay/unify-rope-sycl
June 14, 2024 12:30 10m 30s
Replace powf with sycl::pow in ggml-sycl.cpp Code Coverage #13216: Commit ded54b5 pushed by joeatodd
June 14, 2024 12:30 4m 37s codeplay/unify-rope-sycl
codeplay/unify-rope-sycl
June 14, 2024 12:30 4m 37s
update: support Qwen2-57B-A14B Code Coverage #13215: Pull request #7835 synchronize by legraphista
June 14, 2024 11:38 20m 12s legraphista:master
legraphista:master
June 14, 2024 11:38 20m 12s
Fix conversion of unnormalized BF16->BF16 weights Code Coverage #13214: Pull request #7843 synchronize by CISC
June 14, 2024 11:32 4m 20s CISC:convert-bf16-fix
CISC:convert-bf16-fix
June 14, 2024 11:32 4m 20s
llama : more checks before assuming FIM tokens (#7644) Code Coverage #13211: Commit 6fcd133 pushed by ggerganov
June 14, 2024 10:20 1h 5m 46s master
master
June 14, 2024 10:20 1h 5m 46s