Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
3,459 workflow run results
3,459 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

tool-call: allow --chat-template chatml w/ --jinja, default to chatml upon parsing issue, avoid double bos CI #19054: Pull request #11616 synchronize by ochafik
28m 56s ochafik:jinja-chatml
ochafik:jinja-chatml
28m 56s
tool-call: allow --chat-template chatml w/ --jinja, default to chatml upon parsing issue, avoid double bos CI #19053: Pull request #11616 synchronize by ochafik
2m 59s ochafik:jinja-chatml
ochafik:jinja-chatml
2m 59s
server : add handle_slot_type lambda CI #19052: Pull request #11535 synchronize by danbev
36m 54s danbev:server-handle_slot_type_lambda
danbev:server-handle_slot_type_lambda
36m 54s
De-duplicate fmt and format functions and optimize CI #19051: Pull request #11596 synchronize by ericcurtin
32m 15s optimize_fmt
optimize_fmt
32m 15s
De-duplicate fmt and format functions and optimize CI #19050: Pull request #11596 synchronize by ericcurtin
1m 16s optimize_fmt
optimize_fmt
1m 16s
SYCL: Kernel function refactor CI #19049: Pull request #11515 synchronize by qnixsynapse
31m 3s qnixsynapse:refactor_kernels
qnixsynapse:refactor_kernels
31m 3s
SYCL: Kernel function refactor CI #19048: Pull request #11515 synchronize by qnixsynapse
5m 52s qnixsynapse:refactor_kernels
qnixsynapse:refactor_kernels
5m 52s
CUDA: fix Volta FlashAttention logic (#11615) CI #19047: Commit 21c84b5 pushed by ggerganov
39m 31s master
master
39m 31s
llama : refactor llama_kv_cache, llama_context and llm_build_context CI #19046: Pull request #11213 synchronize by ggerganov
38m 35s gg/llama-kv-cache
gg/llama-kv-cache
38m 35s
CUDA: fix Volta FlashAttention logic CI #19045: Pull request #11615 synchronize by JohannesGaessler
41m 22s JohannesGaessler:cuda-fa-fix-logic
JohannesGaessler:cuda-fa-fix-logic
41m 22s
llama : fix rwkv inference in gg/llama-kv-cache branch CI #19044: Pull request #11618 synchronize by MollySophia
1h 1m 52s MollySophia:molly/llama-kv-cache
MollySophia:molly/llama-kv-cache
1h 1m 52s
De-duplicate fmt and format functions and optimize CI #19043: Pull request #11596 synchronize by ericcurtin
41m 44s optimize_fmt
optimize_fmt
41m 44s
tool-call: command r7b fix for normal responses CI #19042: Pull request #11608 synchronize by ochafik
33m 30s ochafik:c7rb-fix
ochafik:c7rb-fix
33m 30s
llama : fix rwkv inference in gg/llama-kv-cache branch CI #19041: Pull request #11618 opened by MollySophia
4m 28s MollySophia:molly/llama-kv-cache
MollySophia:molly/llama-kv-cache
4m 28s
De-duplicate fmt and format functions and optimize CI #19040: Pull request #11596 synchronize by ericcurtin
1m 58s optimize_fmt
optimize_fmt
1m 58s
ci: add bash script to check if llama-impl.h was included erroneously CI #19039: Pull request #11617 opened by mofosyne
32m 34s mofosyne:precompile-check-includes-exclusion-from-example
mofosyne:precompile-check-includes-exclusion-from-example
32m 34s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19038: Pull request #11607 synchronize by ochafik
14m 48s ochafik:r1-toolcall
ochafik:r1-toolcall
14m 48s
tool-call: allow --chat-template chatml w/ --jinja, default to chatml upon parsing issue, avoid double bos CI #19037: Pull request #11616 opened by ochafik
43m 41s ochafik:jinja-chatml
ochafik:jinja-chatml
43m 41s
CUDA: fix Volta FlashAttention logic CI #19036: Pull request #11615 opened by JohannesGaessler
32m 6s JohannesGaessler:cuda-fa-fix-logic
JohannesGaessler:cuda-fa-fix-logic
32m 6s
SYCL: Kernel function refactor CI #19035: Pull request #11515 synchronize by qnixsynapse
28m 36s qnixsynapse:refactor_kernels
qnixsynapse:refactor_kernels
28m 36s
tool-call: command r7b fix for normal responses CI #19034: Pull request #11608 synchronize by ochafik
36m 4s ochafik:c7rb-fix
ochafik:c7rb-fix
36m 4s
tool-call: command r7b fix for normal responses CI #19033: Pull request #11608 opened by ochafik
13m 39s ochafik:c7rb-fix
ochafik:c7rb-fix
13m 39s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19032: Pull request #11607 synchronize by ochafik
34m 17s ochafik:r1-toolcall
ochafik:r1-toolcall
34m 17s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19031: Pull request #11607 opened by ochafik
5m 29s ochafik:r1-toolcall
ochafik:r1-toolcall
5m 29s
add --rpc-layers flag to explicitly set RPC layers CI #19030: Pull request #11606 opened by kallewoof
30m 31s dgarage:202502-nrl-param
dgarage:202502-nrl-param
30m 31s
ProTip! You can narrow down the results and go further in time using created:<2025-02-03 or the other filters available.