Skip to content

Actions: ggml-org/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
server : remove /api endpoints Server #31586: Pull request #22165 opened by ggerganov
Queued gg/server-remove-api
gg/server-remove-api
Queued
common: improve GGUF quantization tag regex Server #31585: Pull request #22164 opened by v1b3coder
Action required v1b3coder:fix/gguf-tag-regex
v1b3coder:fix/gguf-tag-regex
Action required
Tensor-parallel: Fix delayed AllReduce on Gemma-4 MoE Server #31583: Pull request #22129 synchronize by gaugarg-nv
Queued gaugarg-nv:gemma4_perf
gaugarg-nv:gemma4_perf
Queued
server: Allow continue in thinking (reasoning prefill) Server #31582: Pull request #22162 synchronize by roj234
Action required roj234:thinking_prefill
roj234:thinking_prefill
Action required
server: Allow continue in thinking (reasoning prefill) Server #31581: Pull request #22162 synchronize by roj234
Action required roj234:thinking_prefill
roj234:thinking_prefill
Action required
server: Allow continue in thinking (reasoning prefill) Server #31580: Pull request #22162 opened by roj234
Action required roj234:thinking_prefill
roj234:thinking_prefill
Action required
TP: fix 0-sized tensor slices, AllReduce fallback Server #31579: Pull request #21808 synchronize by JohannesGaessler
In progress JohannesGaessler:tp-fix-0-slice
JohannesGaessler:tp-fix-0-slice
In progress
webui: Server tools Server #31578: Pull request #21237 synchronize by allozaur
Queued allozaur:allozaur/20677-webui-server-tools
allozaur:allozaur/20677-webui-server-tools
Queued
mtmd: refactor mtmd_decode_use_mrope Server #31577: Pull request #22161 opened by ngxson
1h 4m 31s ngxson:xsn/mtmd_refactor_mrope
ngxson:xsn/mtmd_refactor_mrope
1h 4m 31s
rpc : implement event and async backend APIs Server #31576: Pull request #18626 synchronize by rgerganov
1h 4m 35s rgerganov:rpc-async
rgerganov:rpc-async
1h 4m 35s
webui: Server tools Server #31575: Pull request #21237 synchronize by allozaur
43m 12s allozaur:allozaur/20677-webui-server-tools
allozaur:allozaur/20677-webui-server-tools
43m 12s
mtmd, llama : Update HunyuanVL vision-language model support Server #31574: Pull request #22037 synchronize by wendadawen
Action required ManaEstras:pr2-hunyuanvl
ManaEstras:pr2-hunyuanvl
Action required
webui: Server tools Server #31573: Pull request #21237 synchronize by allozaur
55m 46s allozaur:allozaur/20677-webui-server-tools
allozaur:allozaur/20677-webui-server-tools
55m 46s
webui: Server tools Server #31572: Pull request #21237 synchronize by allozaur
12m 22s allozaur:allozaur/20677-webui-server-tools
allozaur:allozaur/20677-webui-server-tools
12m 22s
Make llama_token_to_piece return INT32_MIN for invalid tokens Server #31569: Pull request #22121 synchronize by julmb
Action required julmb:bounds
julmb:bounds
Action required
Support for DeepseekV32ForCausalLM with DeepSeek Sparse Attention (DSA) Server #31568: Pull request #21149 synchronize by fairydreaming
2h 41m 32s fairydreaming:deepseek-dsa
fairydreaming:deepseek-dsa
2h 41m 32s
fix: GLM-DSA crash in llama-tokenize when using vocab_only (#22102) Server #31567: Commit 81df3f7 pushed by ggerganov
3h 22m 3s master
master
3h 22m 3s
sycl: scalar SWAR byte-subtract in Q6_K MMVQ dot product Server #31566: Pull request #22156 opened by aicss-genai
Action required aicss-genai:aicss-genai/sycl-bmg-upstream-pr-7
aicss-genai:aicss-genai/sycl-bmg-upstream-pr-7
Action required
ggml-cuda: flush legacy pool on OOM and retry Server #31565: Pull request #22155 opened by leonardHONG
Action required leonardHONG:cuda-pool-leg-oom-retry
leonardHONG:cuda-pool-leg-oom-retry
Action required
server: Support chat_template_kwargs for /v1/messages Server #31564: Pull request #22154 opened by Soreepeong
In progress Soreepeong:anthropic-oai-conv-chat-template-kwargs
Soreepeong:anthropic-oai-conv-chat-template-kwargs
In progress
sycl: add GGML_SYCL_USE_ASYNC_MEM_OP env toggle Server #31563: Pull request #22153 opened by aicss-genai
Action required aicss-genai:aicss-genai/sycl-bmg-upstream-pr-6
aicss-genai:aicss-genai/sycl-bmg-upstream-pr-6
Action required
sycl: Q5_K reorder MMVQ/dequant + Q8_0 reorder MMVQ path Server #31562: Pull request #22152 opened by aicss-genai
Action required aicss-genai:aicss-genai/sycl-bmg-upstream-pr-5
aicss-genai:aicss-genai/sycl-bmg-upstream-pr-5
Action required
sycl: route small f32 matmuls to oneMKL, bypass oneDNN Server #31561: Pull request #22150 opened by aicss-genai
Action required aicss-genai:aicss-genai/sycl-bmg-upstream-pr-4
aicss-genai:aicss-genai/sycl-bmg-upstream-pr-4
Action required
spec: save the dynamic/static ngram cache file Server #31560: Pull request #22055 synchronize by petersid2022
Action required petersid2022:self-speculation-save-cache
petersid2022:self-speculation-save-cache
Action required
sycl: add FILL, CUMSUM, DIAG, SOLVE_TRI, SSM_SCAN, GATED_DELTA_NET Server #31559: Pull request #22149 opened by aicss-genai
Action required aicss-genai:aicss-genai/sycl-bmg-upstream-pr-3
aicss-genai:aicss-genai/sycl-bmg-upstream-pr-3
Action required