Skip to content

Actions: ngxson/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
1,588 workflow run results
1,588 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: coopmat2 mul_mat optimizations (#14934) Server #1946: Commit 4cb208c pushed by ngxson
15m 26s master
master
15m 26s
vulkan: Support ne[3]>1 in noncontig matrix-vector multiply (#15015) Server #1945: Commit ec0b188 pushed by ngxson
21m 0s master
master
21m 0s
model : support Qwen3-Embedding (#15023) Server #1944: Commit 339bd02 pushed by ngxson
18m 53s master
master
18m 53s
server: enable token array inputs for OAI API (#15001) Server #1943: Commit f906275 pushed by ngxson
14m 4s master
master
14m 4s
vulkan: optimizations for direct convolution (#14933) Server #1942: Commit a9f7541 pushed by ngxson
17m 28s master
master
17m 28s
vendor : update vendored copy of google/minja (#15011) Server #1941: Commit c76b420 pushed by ngxson
12m 27s master
master
12m 27s
model : add hunyuan dense (#14878) Server #1940: Commit 0f5ccd6 pushed by ngxson
12m 42s master
master
12m 42s
opencl: add f16 for add, sub, mul, div (#14984) Server #1939: Commit 1c872f7 pushed by ngxson
11m 46s master
master
11m 46s
ggml : Q2k interleaving implementation - x86/x64 SIMD (#14373) Server #1938: Commit baad948 pushed by ngxson
12m 43s master
master
12m 43s
graph : fix equal_seq() check (#14986) Server #1937: Commit ba42794 pushed by ngxson
12m 15s master
master
12m 15s
docker : add cann build pipline (#14591) Server #1936: Commit 2860d47 pushed by ngxson
12m 39s master
master
12m 39s
quantize : skip tensor override when in fallback mode (#14995) Server #1935: Commit daf2dd7 pushed by ngxson
11m 38s master
master
11m 38s
llama : add simple option to enable CPU for MoE weights (--cpu-moe) (… Server #1934: Commit a06ed5f pushed by ngxson
11m 30s master
master
11m 30s
Fix params bug in diffusion example (#14993) Server #1933: Commit 7845240 pushed by ngxson
12m 3s master
master
12m 3s
llama : allow other bufts when overriding to CPU, add --no-repack opt… Server #1932: Commit d6818d0 pushed by ngxson
11m 45s master
master
11m 45s
Vulkan: Fix minor debug mode issues (#14899) Server #1931: Commit e08a988 pushed by ngxson
12m 28s master
master
12m 28s
mtmd : support MiniCPM-V 4.0 (#14983) Server #1930: Commit 952a47f pushed by ngxson
11m 55s master
master
11m 55s
server : implement universal assisted decoding (#12635) Server #1929: Commit 94933c8 pushed by ngxson
34m 18s master
master
34m 18s
llama : merge build_moe_ffn_from_probs function into build_moe_ffn (#… Server #1928: Commit c1dacaa pushed by ngxson
40m 51s master
master
40m 51s
server : add openai-style logit_bias support (#14946) Server #1927: Commit a9f77a8 pushed by ngxson
20m 44s master
master
20m 44s
Add LLaDA 8b Diffusion model (#14771) Server #1926: Commit 8a4a856 pushed by ngxson
23m 47s master
master
23m 47s
graph : reduce splits for recurrent and hybrid models (#14825) Server #1925: Commit 66625a5 pushed by ngxson
11m 34s master
master
11m 34s
opencl: add mul_mat_f32_f32_l4_lm and mul_mat_f16_f32_l4_lm (#14809) Server #1924: Commit 6e67254 pushed by ngxson
12m 34s master
master
12m 34s
quantize : fix using combined imatrix GGUFs (multiple datasets) (#14973) Server #1923: Commit e9192be pushed by ngxson
12m 52s master
master
12m 52s
server : add support for embd_normalize parameter (#14964) Server #1922: Commit 41e78c5 pushed by ngxson
12m 46s master
master
12m 46s