Skip to content

Actions: ggml-org/llama.cpp

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-tokenizer-hashes.yml
412 workflow run results
412 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Model: Add support for Seed-OSS Check Pre-Tokenizer Hashes #144: Pull request #15490 synchronize by pwilkin
1m 4s pwilkin:seed_oss
pwilkin:seed_oss
1m 4s
Add DeepSeek-V3.1 Check Pre-Tokenizer Hashes #143: Pull request #15495 synchronize by createthis
32s createthis:add_deepseek_3_1
createthis:add_deepseek_3_1
32s
Model: Add support for Seed-OSS Check Pre-Tokenizer Hashes #140: Pull request #15490 synchronize by pwilkin
34s pwilkin:seed_oss
pwilkin:seed_oss
34s
Model: Add support for Seed-OSS Check Pre-Tokenizer Hashes #139: Pull request #15490 synchronize by pwilkin
37s pwilkin:seed_oss
pwilkin:seed_oss
37s
Model: Add support for Seed-OSS Check Pre-Tokenizer Hashes #138: Pull request #15490 synchronize by pwilkin
42s pwilkin:seed_oss
pwilkin:seed_oss
42s
Model: Add support for Seed-OSS Check Pre-Tokenizer Hashes #137: Pull request #15490 opened by pwilkin
31s pwilkin:seed_oss
pwilkin:seed_oss
31s
llama : remove KV cache defragmentation logic Check Pre-Tokenizer Hashes #136: Commit d6588a8 pushed by ggerganov
2m 0s gg/remove-defrag
gg/remove-defrag
2m 0s
llama : remove deprecated llama_kv_self API Check Pre-Tokenizer Hashes #135: Commit 3a3a93d pushed by ggerganov
51m 30s gg/kv-self-remove-api
gg/kv-self-remove-api
51m 30s
vulkan: use prealloc intermediate reuse for mmvq path Check Pre-Tokenizer Hashes #134: Commit 730ba00 pushed by 0cc4m
25m 5s 0cc4m/vulkan-mmq-dp4a-vec
0cc4m/vulkan-mmq-dp4a-vec
25m 5s
graph : remove build_attn_with_sinks overload Check Pre-Tokenizer Hashes #133: Commit 3827a76 pushed by ggerganov
12m 5s gg/graph-remove-with-sinks
gg/graph-remove-with-sinks
12m 5s
convert : make Mistral community chat templates optional via paramete… Check Pre-Tokenizer Hashes #132: Commit b2caf67 pushed by CISC
3m 17s master
master
3m 17s
mtmd : support Kimi VL model Check Pre-Tokenizer Hashes #131: Pull request #15458 synchronize by ngxson
53s ngxson:xsn/kimi-vl
ngxson:xsn/kimi-vl
53s
mtmd : support Kimi VL model Check Pre-Tokenizer Hashes #130: Pull request #15458 opened by ngxson
15m 39s ngxson:xsn/kimi-vl
ngxson:xsn/kimi-vl
15m 39s
convert : handle pre-quantized models Check Pre-Tokenizer Hashes #128: Pull request #14810 synchronize by compilade
32s compilade/convert-prequant
compilade/convert-prequant
32s
convert : fix conversion from FP8 for Deepseek-V3.1-Base Check Pre-Tokenizer Hashes #127: Commit 8993982 pushed by compilade
30s compilade/convert-prequant
compilade/convert-prequant
30s
Make Mistral community chat templates optional Check Pre-Tokenizer Hashes #126: Pull request #15420 synchronize by juliendenize
32s juliendenize:make_mistral_templates_optional
juliendenize:make_mistral_templates_optional
32s
Make Mistral community chat templates optional Check Pre-Tokenizer Hashes #125: Pull request #15420 synchronize by juliendenize
8m 28s juliendenize:make_mistral_templates_optional
juliendenize:make_mistral_templates_optional
8m 28s
Make Mistral community chat templates optional Check Pre-Tokenizer Hashes #124: Pull request #15420 synchronize by juliendenize
9m 43s juliendenize:make_mistral_templates_optional
juliendenize:make_mistral_templates_optional
9m 43s
Make Mistral community chat templates optional Check Pre-Tokenizer Hashes #123: Pull request #15420 synchronize by juliendenize
11m 42s juliendenize:make_mistral_templates_optional
juliendenize:make_mistral_templates_optional
11m 42s
Make Mistral community chat templates optional Check Pre-Tokenizer Hashes #122: Pull request #15420 opened by juliendenize
11m 3s juliendenize:make_mistral_templates_optional
juliendenize:make_mistral_templates_optional
11m 3s
support interns1-mini Check Pre-Tokenizer Hashes #121: Pull request #15412 opened by RunningLeon
32s RunningLeon:interns1-mini
RunningLeon:interns1-mini
32s
vulkan: tune mul_mat_vecq performance for Intel Check Pre-Tokenizer Hashes #120: Commit afc464a pushed by 0cc4m
33s 0cc4m/vulkan-mmq-dp4a-vec
0cc4m/vulkan-mmq-dp4a-vec
33s
convert : force patch_embd weights to F16 or F32 to avoid broken GGUF… Check Pre-Tokenizer Hashes #119: Commit 4d19698 pushed by CISC
30s master
master
30s
convert : force patch_embd weights to F16 or F32 to avoid broken GGUFs Check Pre-Tokenizer Hashes #118: Pull request #15367 synchronize by CISC
32s cisc/fix-convert-mmproj-patch-embd
cisc/fix-convert-mmproj-patch-embd
32s
use MmprojModel base tensor_force_quant instead Check Pre-Tokenizer Hashes #117: Commit 28722d1 pushed by CISC
29s cisc/fix-convert-mmproj-patch-embd
cisc/fix-convert-mmproj-patch-embd
29s
ProTip! You can narrow down the results and go further in time using created:<2025-08-17 or the other filters available.