Skip to content

Actions: YannFollet/llama.cpp

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
29 workflow runs
29 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : support RWKV v6 models (#8980)
CI #42: Commit 8f1d81a pushed by YannFollet
September 2, 2024 03:57 1h 3m 53s master
September 2, 2024 03:57 1h 3m 53s
ggml : add epsilon as a parameter for group_norm (#8818)
CI #41: Commit 2d5dd7b pushed by YannFollet
August 6, 2024 08:45 1h 7m 25s master
August 6, 2024 08:45 1h 7m 25s
cmake: use 1 more thread for non-ggml in CI (#8740)
CI #40: Commit 6eeaeba pushed by YannFollet
July 29, 2024 02:32 1h 2m 0s master
July 29, 2024 02:32 1h 2m 0s
server : add Speech Recognition & Synthesis to UI (#8679)
CI #39: Commit 01aec4a pushed by YannFollet
July 26, 2024 01:53 55m 42s master
July 26, 2024 01:53 55m 42s
flake.lock: Update (#8610)
CI #38: Commit 45f2c19 pushed by YannFollet
July 22, 2024 03:53 58m 30s master
July 22, 2024 03:53 58m 30s
gguf_dump.py: fix markddown kv array print (#8588)
CI #37: Commit c3776ca pushed by YannFollet
July 20, 2024 11:50 47m 55s master
July 20, 2024 11:50 47m 55s
disable publishing the full-rocm docker image (#8083)
CI #36: Commit 8cb508d pushed by YannFollet
June 24, 2024 07:53 42m 3s master
June 24, 2024 07:53 42m 3s
llama : add support for BitnetForCausalLM (#7931)
CI #35: Commit e112b61 pushed by YannFollet
June 24, 2024 00:58 38m 49s master
June 24, 2024 00:58 38m 49s
server : fix smart slot selection (#8020)
CI #34: Commit ba58993 pushed by YannFollet
June 20, 2024 02:22 41m 5s master
June 20, 2024 02:22 41m 5s
chore: clean useless beam search param (#7985)
CI #33: Commit b96f9af pushed by YannFollet
June 18, 2024 08:34 41m 22s master
June 18, 2024 08:34 41m 22s
Somehow '**' got lost (#7663)
CI #32: Commit 2e32f87 pushed by YannFollet
May 31, 2024 10:58 35m 2s master
May 31, 2024 10:58 35m 2s
add build shared lib in win release package (#7438)
CI #31: Commit 0df0aa8 pushed by YannFollet
May 24, 2024 07:40 36m 28s master
May 24, 2024 07:40 36m 28s
CUDA: fix FA out-of-bounds reads (#7479)
CI #30: Commit cd93a28 pushed by YannFollet
May 23, 2024 01:45 32m 53s master
May 23, 2024 01:45 32m 53s
CUDA: remove incorrect precision check (#7454)
CI #29: Commit 95fb0ae pushed by YannFollet
May 22, 2024 09:14 38m 38s master
May 22, 2024 09:14 38m 38s
llama : add phi3 128K model support (#7225)
CI #28: Commit 201cc11 pushed by YannFollet
May 22, 2024 02:19 49m 0s master
May 22, 2024 02:19 49m 0s
May 15, 2024 07:04 31m 48s
convert-hf : support direct Q8_0 conversion (#7234)
CI #25: Commit ee52225 pushed by YannFollet
May 14, 2024 01:45 34m 2s master
May 14, 2024 01:45 34m 2s
README: add graphic for matrix multiplication (#6881)
CI #24: Commit 784e11d pushed by YannFollet
April 25, 2024 01:53 33m 32s master
April 25, 2024 01:53 33m 32s
April 22, 2024 06:53 28m 41s
March 26, 2024 07:49 21m 29s
llama : fix integer overflow during quantization (#6063)
CI #21: Commit 4755afd pushed by YannFollet
March 15, 2024 02:33 38m 26s master
March 15, 2024 02:33 38m 26s
ggml : use SYS_get_cpu if SYS_getcpu is not defined (#5906)
CI #20: Commit e04e04f pushed by YannFollet
March 7, 2024 02:21 50m 39s master
March 7, 2024 02:21 50m 39s
ci : reduce 3b ppl chunks to 1 to avoid timeout (#5771)
CI #19: Commit 87c91c0 pushed by YannFollet
February 29, 2024 02:59 32m 33s master
February 29, 2024 02:59 32m 33s
readme : update hot topics
CI #18: Commit 56d03d9 pushed by YannFollet
February 22, 2024 10:28 26m 1s master
February 22, 2024 10:28 26m 1s