Skip to content

Actions: ngxson/llama.cpp

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-tokenizer-hashes.yml
44 workflow runs
44 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Merge branch 'master' into xsn/homecook-mistral-o Check Pre-Tokenizer Hashes #44: Commit 15a0170 pushed by ngxson
8m 38s xsn/homecook-mistral-o
xsn/homecook-mistral-o
8m 38s
convert : correctly handle LLaMA tokenizer for Jamba (#16470) Check Pre-Tokenizer Hashes #43: Commit 477a66b pushed by ngxson
56s master
master
56s
model: EmbeddingGemma Adding Support for SentenceTransformers Dense M… Check Pre-Tokenizer Hashes #42: Commit e08db42 pushed by ngxson
10m 43s master
master
10m 43s
llama : support LiquidAI LFM2-MoE hybrid model (#16464) Check Pre-Tokenizer Hashes #41: Commit aeaf8a3 pushed by ngxson
1m 4s master
master
1m 4s
model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206) Check Pre-Tokenizer Hashes #40: Commit ca71fb9 pushed by ngxson
51s master
master
51s
model : Apertus model implementation (#15852) Check Pre-Tokenizer Hashes #39: Commit 34fcc5a pushed by ngxson
54s master
master
54s
HIP: Disable ROCWMMA fattn on CDNA when compiled against ROCWMMA 2.0.… Check Pre-Tokenizer Hashes #38: Commit e95fec6 pushed by ngxson
53s master
master
53s
model : add GroveMoE support (#15510) Check Pre-Tokenizer Hashes #37: Commit 835b2b9 pushed by ngxson
1m 8s master
master
1m 8s
llama : add support for qwen3 reranker (#15824) Check Pre-Tokenizer Hashes #36: Commit b5bd037 pushed by ngxson
50s master
master
50s
feat: Add conversion support in GraniteHybrid for non-hybrid (all att… Check Pre-Tokenizer Hashes #35: Commit 1d0125b pushed by ngxson
58s master
master
58s
convert : add Llama4ForCausalLM (#16042) Check Pre-Tokenizer Hashes #34: Commit 8f8f227 pushed by ngxson
1m 3s master
master
1m 3s
model : add OLMo3 support (#16015) Check Pre-Tokenizer Hashes #33: Commit 85286f3 pushed by ngxson
49s master
master
49s
half working version Check Pre-Tokenizer Hashes #32: Commit c540db6 pushed by ngxson
52s xsn/llama4causalfix
xsn/llama4causalfix
52s
convert : add Llama4ForCausalLM Check Pre-Tokenizer Hashes #31: Commit 66fe9ff pushed by ngxson
51s xsn/llama4causalfix
xsn/llama4causalfix
51s
convert : add Llama4ForCausalLM Check Pre-Tokenizer Hashes #30: Commit bba0e61 pushed by ngxson
31s xsn/llama4causal
xsn/llama4causal
31s
Add LLaDA-7b-MoE diffusion model (#16003) Check Pre-Tokenizer Hashes #29: Commit 6d75883 pushed by ngxson
53s master
master
53s
model : add grok-2 support (#15539) Check Pre-Tokenizer Hashes #28: Commit b8e09f0 pushed by ngxson
7m 43s master
master
7m 43s
llama : support T5 models with unequal number of encoder-decoder laye… Check Pre-Tokenizer Hashes #27: Commit 4f65885 pushed by ngxson
54s master
master
54s
convert : force setting sliding_window from original config (#15867) Check Pre-Tokenizer Hashes #26: Commit 233d773 pushed by ngxson
31s master
master
31s
llama : add support for EmbeddingGemma 300m (#15798) Check Pre-Tokenizer Hashes #25: Commit fb15d64 pushed by ngxson
45s master
master
45s
convert : remove redundant code (#15708) Check Pre-Tokenizer Hashes #24: Commit 4b20d8b pushed by ngxson
33s master
master
33s
nvidia nemotron nano v2 (nemotronh) (#15507) Check Pre-Tokenizer Hashes #23: Commit e8d99dd pushed by ngxson
29s master
master
29s
mtmd : support Kimi VL model (#15458) Check Pre-Tokenizer Hashes #22: Commit 79a5462 pushed by ngxson
30s master
master
30s
convert : update Ernie 4.5 dense architecture name (#15555) Check Pre-Tokenizer Hashes #21: Commit 0d5a470 pushed by ngxson
33s master
master
33s
convert : support interns1-mini (#15412) Check Pre-Tokenizer Hashes #20: Commit 7da9fed pushed by ngxson
30s master
master
30s