Skip to content

Actions: ggerganov/llama.cpp

Actions

Server

Actions

Loading...

Show workflow options

Create status badge

server.yml
5,988 workflow runs
5,988 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml : do not crash when quantizing q4_x_x with an imatrix Server #6259: Pull request #9192 opened by slaren
August 26, 2024 14:59 In progress sl/fix-q4xx-imatrix
sl/fix-q4xx-imatrix
August 26, 2024 14:59 In progress
ggml : add SSM Metal kernels (#8546) Server #6258: Commit fc18425 pushed by ggerganov
August 26, 2024 14:55 42m 38s master
master
August 26, 2024 14:55 42m 38s
tests : fix compile warnings for unreachable code (#9185) Server #6257: Commit 879275a pushed by ggerganov
August 26, 2024 13:30 22m 10s master
master
August 26, 2024 13:30 22m 10s
tokenize : add --show-count-only (token) option Server #6256: Pull request #9182 synchronize by danbev
August 26, 2024 11:39 1h 19m 35s danbev:show-token-count-only
danbev:show-token-count-only
August 26, 2024 11:39 1h 19m 35s
ggml:Mamba Cuda kernel performance improve Server #6255: Pull request #9186 opened by piDack
August 26, 2024 09:42 2h 43m 46s piDack:mfalcon_mamba_cuda
piDack:mfalcon_mamba_cuda
August 26, 2024 09:42 2h 43m 46s
tests : fix compile warnings for unreachable code Server #6254: Pull request #9185 opened by ggerganov
August 26, 2024 09:30 1h 33m 12s gg/tests-fix-unreach
gg/tests-fix-unreach
August 26, 2024 09:30 1h 33m 12s
server : update deps (#9183) Server #6253: Commit e5edb21 pushed by ggerganov
August 26, 2024 09:17 1h 11m 5s master
master
August 26, 2024 09:17 1h 11m 5s
metal : gemma2 flash attention support (#9159) Server #6252: Commit 0c41e03 pushed by slaren
August 26, 2024 09:09 31m 37s master
master
August 26, 2024 09:09 31m 37s
metal : gemma2 flash attention support Server #6251: Pull request #9159 synchronize by slaren
August 26, 2024 08:51 25m 3s sl/metal-logit-softcap
sl/metal-logit-softcap
August 26, 2024 08:51 25m 3s
ggml : remove K_QUANTS_PER_ITERATION macro Server #6250: Pull request #9034 synchronize by ggerganov
August 26, 2024 06:52 8m 57s gg/remove-k-quants-per-iter
gg/remove-k-quants-per-iter
August 26, 2024 06:52 8m 57s
server : update deps Server #6249: Pull request #9183 opened by ggerganov
August 26, 2024 06:17 28m 18s gg/server-update-deps
gg/server-update-deps
August 26, 2024 06:17 28m 18s
llama : fix time complexity of string replacement (#9163) Server #6248: Commit 436787f pushed by ggerganov
August 26, 2024 06:09 9m 42s master
master
August 26, 2024 06:09 9m 42s
tokenize : add --show-count-only (token) option Server #6247: Pull request #9182 opened by danbev
August 26, 2024 05:25 9m 39s danbev:show-token-count-only
danbev:show-token-count-only
August 26, 2024 05:25 9m 39s
Threadpool: take 2 Server #6246: Pull request #8672 synchronize by max-krasnyansky
August 26, 2024 04:37 20m 18s CodeLinaro:threadpool
CodeLinaro:threadpool
August 26, 2024 04:37 20m 18s
llama : support RWKV v6 models Server #6245: Pull request #8980 synchronize by MollySophia
August 26, 2024 01:53 9m 30s MollySophia:for-upstream
MollySophia:for-upstream
August 26, 2024 01:53 9m 30s
llama : support RWKV v6 models Server #6244: Pull request #8980 synchronize by MollySophia
August 26, 2024 01:51 2m 7s MollySophia:for-upstream
MollySophia:for-upstream
August 26, 2024 01:51 2m 7s
llama : support RWKV v6 models Server #6243: Pull request #8980 synchronize by MollySophia
August 26, 2024 01:32 10m 12s MollySophia:for-upstream
MollySophia:for-upstream
August 26, 2024 01:32 10m 12s
llama: changed default type IQ2_XS to IQ2_S for LLAMA_FTYPE_MOSTLY_IQ2_S Server #6242: Pull request #9179 opened by GermanAizek
August 26, 2024 00:19 9m 32s GermanAizek:fix-default-type
GermanAizek:fix-default-type
August 26, 2024 00:19 9m 32s
ggml: skip excess iteration for pair whose vars same element when i2 == i1 Server #6241: Pull request #9177 opened by GermanAizek
August 25, 2024 23:46 9m 27s GermanAizek:optimize-quantize-iq1
GermanAizek:optimize-quantize-iq1
August 25, 2024 23:46 9m 27s
common,train,examples: using C++17 constexpr string and strlen Server #6240: Pull request #9176 opened by GermanAizek
August 25, 2024 23:24 9m 31s GermanAizek:constexpr
GermanAizek:constexpr
August 25, 2024 23:24 9m 31s
common: fixed not working find argument --n-gpu-layers-draft (#9175) Server #6239: Commit 93bc383 pushed by JohannesGaessler
August 25, 2024 22:54 9m 36s master
master
August 25, 2024 22:54 9m 36s
common: fixed not working find argument --n-gpu-layers-draft Server #6238: Pull request #9175 opened by GermanAizek
August 25, 2024 22:10 9m 34s GermanAizek:fix-arg
GermanAizek:fix-arg
August 25, 2024 22:10 9m 34s
CUDA: fix Gemma 2 numerical issues for FA (#9166) Server #6237: Commit f91fc56 pushed by JohannesGaessler
August 25, 2024 20:11 9m 19s master
master
August 25, 2024 20:11 9m 19s
Add GGML_USE_BLAS flag to llama.cpp and update BLAS documentation to allow GPU usage on Macbooks with Intel GPUs Server #6236: Pull request #9081 synchronize by simonteozw
August 25, 2024 15:22 Action required simonteozw:blas_gpu
simonteozw:blas_gpu
August 25, 2024 15:22 Action required
Changes for the existing quant strategies / FTYPEs and new ones Server #6235: Pull request #8836 synchronize by Nexesenex
August 25, 2024 12:27 10m 1s Nexesenex:patch-1
Nexesenex:patch-1
August 25, 2024 12:27 10m 1s