Skip to content

Actions: ggerganov/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
8,937 workflow runs
8,937 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: experimental coalesced read to shared memory before dequantization Server #9391: Pull request #10999 opened by netrunnereve
December 27, 2024 22:34 5m 28s netrunnereve:kquant_optimizations
netrunnereve:kquant_optimizations
December 27, 2024 22:34 5m 28s
server : allow using LoRA adapters per-request Server #9390: Pull request #10994 synchronize by ngxson
December 27, 2024 19:22 4m 42s ngxson:xsn/lora_per_request
ngxson:xsn/lora_per_request
December 27, 2024 19:22 4m 42s
server : fix token duplication when streaming with stop strings Server #9389: Pull request #10997 opened by z80maniac
December 27, 2024 19:05 8m 13s z80maniac:dup-fix
z80maniac:dup-fix
December 27, 2024 19:05 8m 13s
server : allow using LoRA adapters per-request Server #9388: Pull request #10994 synchronize by ngxson
December 27, 2024 17:35 8m 26s ngxson:xsn/lora_per_request
ngxson:xsn/lora_per_request
December 27, 2024 17:35 8m 26s
server: added more docs for response_fields field Server #9387: Pull request #10995 opened by isaac-mcfadyen
December 27, 2024 15:14 11m 25s isaac-mcfadyen:response-fields-docs
isaac-mcfadyen:response-fields-docs
December 27, 2024 15:14 11m 25s
server : allow using LoRA adapters per-request Server #9386: Pull request #10994 opened by ngxson
December 27, 2024 15:12 6m 28s ngxson:xsn/lora_per_request
ngxson:xsn/lora_per_request
December 27, 2024 15:12 6m 28s
common, examples, ggml : fix MSYS2 GCC compiler errors and warnings when building with LLAMA_CURL=ON and GGML_OPENCL=ON Server #9385: Pull request #10992 synchronize by peter277
December 27, 2024 11:35 6m 31s peter277:master
peter277:master
December 27, 2024 11:35 6m 31s
server: bench: minor fixes Server #9384: Pull request #10765 synchronize by phymbert
December 27, 2024 10:11 4m 30s phymbert/server/bench/fix-streaming
phymbert/server/bench/fix-streaming
December 27, 2024 10:11 4m 30s
Tool call support (Llama 3.x, Functionary v3, Hermes 2 Pro, Mistral Nemo, generic) w/ lazy grammars & minimalist Jinja engine Server #9383: Pull request #9639 synchronize by ochafik
December 27, 2024 02:21 8m 16s ochafik:tool-call
ochafik:tool-call
December 27, 2024 02:21 8m 16s
common, examples, ggml : fix MSYS2 GCC compiler errors and warnings when building with LLAMA_CURL=ON and GGML_OPENCL=ON Server #9382: Pull request #10992 synchronize by peter277
December 27, 2024 01:32 5m 57s peter277:master
peter277:master
December 27, 2024 01:32 5m 57s
common, examples, ggml : fix MSYS2 GCC compiler errors and warnings when building with LLAMA_CURL=ON and GGML_OPENCL=ON Server #9381: Pull request #10992 synchronize by peter277
December 27, 2024 01:31 1m 9s peter277:master
peter277:master
December 27, 2024 01:31 1m 9s
common, examples, ggml : fix MSYS2 GCC compiler errors and warnings when building with LLAMA_CURL=ON and GGML_OPENCL=ON Server #9380: Pull request #10992 opened by peter277
December 27, 2024 01:16 14m 40s peter277:master
peter277:master
December 27, 2024 01:16 14m 40s
Tool call support (Llama 3.x, Functionary v3, Hermes 2 Pro, Mistral Nemo, generic) w/ lazy grammars & minimalist Jinja engine Server #9379: Pull request #9639 synchronize by ochafik
December 27, 2024 00:59 4m 53s ochafik:tool-call
ochafik:tool-call
December 27, 2024 00:59 4m 53s
Introduce Graph Profiler Server #9378: Pull request #9659 synchronize by max-krasnyansky
December 27, 2024 00:09 6m 27s graph-profiler
graph-profiler
December 27, 2024 00:09 6m 27s
vulkan: optimize mul_mat for small values of N Server #9377: Pull request #10991 opened by jeffbolznv
December 26, 2024 22:30 10m 28s jeffbolznv:small_batch_opt
jeffbolznv:small_batch_opt
December 26, 2024 22:30 10m 28s
Tool call support (Llama 3.x, Functionary v3, Hermes 2 Pro, Mistral Nemo, generic) w/ lazy grammars & minimalist Jinja engine Server #9376: Pull request #9639 synchronize by ochafik
December 26, 2024 21:39 3m 50s ochafik:tool-call
ochafik:tool-call
December 26, 2024 21:39 3m 50s
Tool call support (Llama 3.x, Functionary v3, Hermes 2 Pro, Mistral Nemo, generic) w/ lazy grammars & minimalist Jinja engine Server #9375: Pull request #9639 synchronize by ochafik
December 26, 2024 21:26 4m 34s ochafik:tool-call
ochafik:tool-call
December 26, 2024 21:26 4m 34s
Vulkan: Destroy Vulkan instance on exit Server #9374: Pull request #10989 opened by 0cc4m
December 26, 2024 19:17 8m 55s 0cc4m/vulkan-instance-cleanup
0cc4m/vulkan-instance-cleanup
December 26, 2024 19:17 8m 55s
vulkan: Use push constant offset to handle misaligned descriptors Server #9373: Pull request #10987 opened by jeffbolznv
December 26, 2024 17:10 7m 28s jeffbolznv:a_offset
jeffbolznv:a_offset
December 26, 2024 17:10 7m 28s
vulkan: multi-row k quants (#10846) Server #9372: Commit d79d8f3 pushed by 0cc4m
December 26, 2024 15:54 6m 6s master
master
December 26, 2024 15:54 6m 6s
examples, ggml : fix GCC compiler warnings (#10983) Server #9371: Commit d283d02 pushed by slaren
December 26, 2024 13:59 4m 44s master
master
December 26, 2024 13:59 4m 44s
examples, ggml : fix GCC compiler warnings Server #9370: Pull request #10983 synchronize by peter277
December 26, 2024 12:12 5m 35s peter277:master
peter277:master
December 26, 2024 12:12 5m 35s
examples, ggml : fix GCC compiler warnings Server #9369: Pull request #10983 opened by peter277
December 26, 2024 12:08 Action required peter277:master
peter277:master
December 26, 2024 12:08 Action required
llamafile_sgemm API - INT8 implementation Server #9368: Pull request #10912 synchronize by amritahs-ibm
December 26, 2024 10:12 5m 31s amritahs-ibm:sgemm_q8
amritahs-ibm:sgemm_q8
December 26, 2024 10:12 5m 31s
ggml : fix undefined reference to std::filesystem(#10978) Server #9367: Pull request #10979 synchronize by Clauszy
December 26, 2024 07:08 5m 22s Clauszy:master
Clauszy:master
December 26, 2024 07:08 5m 22s