Skip to content

Actions: ServeurpersoCom/llama.cpp

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

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

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

webui: add OAI-Compat Harmony tool-call streaming visualization and p… Check Pre-Tokenizer Hashes #32: Commit a5cff84 pushed by ServeurpersoCom
1m 2s harmony-toolcall-debug-option
harmony-toolcall-debug-option
1m 2s
chore: update webui static build Check Pre-Tokenizer Hashes #31: Commit d13a292 pushed by ServeurpersoCom
58s openai-model-selector
openai-model-selector
58s
webui: address review feedback from allozaur Check Pre-Tokenizer Hashes #30: Commit 05581e8 pushed by ServeurpersoCom
4m 34s testing-branch12
testing-branch12
4m 34s
vulkan: Handle FA with all -inf mask values (#16447) Check Pre-Tokenizer Hashes #29: Commit fb34984 pushed by ServeurpersoCom
56s master
master
56s
Merge qwen3_next into testing-branch10 (took qwen3_next version for s… Check Pre-Tokenizer Hashes #28: Commit 05329e7 pushed by ServeurpersoCom
52s testing-branch10
testing-branch10
52s
Move the norm shift to conversion, Gemma 2 style Check Pre-Tokenizer Hashes #27: Commit c2a82a1 pushed by ServeurpersoCom
56s qwen3_next
qwen3_next
56s
chore: update webui build output Check Pre-Tokenizer Hashes #26: Commit 24ec6ac pushed by ServeurpersoCom
57s fix-markdown-literal-html
fix-markdown-literal-html
57s
Yes, I finally managed to implement it with ssm_conv :> Check Pre-Tokenizer Hashes #25: Commit 232ec56 pushed by ServeurpersoCom
51s qwen3_next
qwen3_next
51s
Update tools/server/webui/src/lib/components/app/chat/ChatScreen/Chat… Check Pre-Tokenizer Hashes #24: Commit be85c24 pushed by ServeurpersoCom
55s ctxsize-rely-on-backend
ctxsize-rely-on-backend
55s
chore: update webui build output Check Pre-Tokenizer Hashes #23: Commit 74e8ee9 pushed by ServeurpersoCom
52s option-user-markdown
option-user-markdown
52s
webui: cosmetic rename of error messages Check Pre-Tokenizer Hashes #22: Commit 73c075a pushed by ServeurpersoCom
2m 55s testing-branch8
testing-branch8
2m 55s
cuda : avoid initializing unused devices (#16510) Check Pre-Tokenizer Hashes #21: Commit 97870e6 pushed by ServeurpersoCom
51s master
master
51s
gguf-viewer: filter min/max to P1-P99 in backend + misc Check Pre-Tokenizer Hashes #20: Commit f6d7b82 pushed by ServeurpersoCom
2m 23s testing-branch8
testing-branch8
2m 23s
ci: add ARM64 Kleidiai build and test support (#16462) Check Pre-Tokenizer Hashes #19: Commit 2c0d875 pushed by ServeurpersoCom
50s master
master
50s
Order stuff around Check Pre-Tokenizer Hashes #18: Commit 17240ea pushed by ServeurpersoCom
49s qwen3_next
qwen3_next
49s
gguf-viewer: contributors https://github.com/ggml-org/llama.cpp/issue… Check Pre-Tokenizer Hashes #17: Commit 7efa2c2 pushed by ServeurpersoCom
50s llama-gguf-viewer
llama-gguf-viewer
50s
gguf-viewer: better layout Check Pre-Tokenizer Hashes #16: Commit 0ef15ce pushed by ServeurpersoCom
17m 5s testing-branch7
testing-branch7
17m 5s
ggml webgpu: profiling, CI updates, reworking of command submission (… Check Pre-Tokenizer Hashes #15: Commit 74b8fc1 pushed by ServeurpersoCom
52s master
master
52s
Update tools/server/webui/src/lib/components/app/chat/ChatMessages/Ch… Check Pre-Tokenizer Hashes #14: Commit 1e6beb6 pushed by ServeurpersoCom
52s streaming-aware-cpp-parser
streaming-aware-cpp-parser
52s
fix: add generic fallback to detect trailing <think> tags in Jinja te… Check Pre-Tokenizer Hashes #13: Commit 0869085 pushed by ServeurpersoCom
1m 0s generic-jinja-think-fallback
generic-jinja-think-fallback
1m 0s
llama-gguf-viewer: better UI Check Pre-Tokenizer Hashes #12: Commit 203fc18 pushed by ServeurpersoCom
12m 21s testing-branch7
testing-branch7
12m 21s
model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206) Check Pre-Tokenizer Hashes #11: Commit ca71fb9 pushed by ServeurpersoCom
52s master
master
52s
refactor: address review feedback from allozaur Check Pre-Tokenizer Hashes #10: Commit 928af2e pushed by ServeurpersoCom
56s streaming-aware-cpp-parser
streaming-aware-cpp-parser
56s
fix: capture freshly selected model in chat store for accurate reply … Check Pre-Tokenizer Hashes #9: Commit 3998da1 pushed by ServeurpersoCom
7m 18s svelte-webui-model-selector
svelte-webui-model-selector
7m 18s
feat: render user content as markdown option Check Pre-Tokenizer Hashes #8: Commit 796c4a8 pushed by ServeurpersoCom
14m 11s option-user-markdown
option-user-markdown
14m 11s