Skip to content

Actions: ggerganov/llama.cpp

Actions

Nix CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
nix-ci.yml
9,176 workflow runs
9,176 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Implementations for Q4_0_8_8 quantization based functions - AVX512 version of ggml_gemm_q4_0_8x8_q8_0 Nix CI #10238: Pull request #9532 synchronize by Srihari-mcw
September 23, 2024 10:16 Queued Srihari-mcw:block_interleaving_q4_0_8_8_gemm_512
Srihari-mcw:block_interleaving_q4_0_8_8_gemm_512
September 23, 2024 10:16 Queued
sampling : avoid expensive softmax during greedy sampling Nix CI #10237: Pull request #9605 opened by ggerganov
September 23, 2024 09:49 In progress gg/sampling-faster-greedy
gg/sampling-faster-greedy
September 23, 2024 09:49 In progress
sampling : fix off-by-one in tail-free sampling Nix CI #10236: Pull request #9604 opened by ggerganov
September 23, 2024 08:49 1h 25m 24s gg/tfs-ob1
gg/tfs-ob1
September 23, 2024 08:49 1h 25m 24s
keep the minimum min_keep value to 1 in sampling Nix CI #10235: Pull request #9603 opened by kylo5aby
September 23, 2024 08:37 1h 18m 39s kylo5aby:min_keep_in_samples
kylo5aby:min_keep_in_samples
September 23, 2024 08:37 1h 18m 39s
perplexity : remove extra new lines after chunks (#9596) Nix CI #10234: Commit 37f8c7b pushed by ggerganov
September 23, 2024 08:28 1h 0m 12s master
master
September 23, 2024 08:28 1h 0m 12s
metal : use F32 prec for K*Q in vec FA (#9595) Nix CI #10233: Commit bf9c101 pushed by ggerganov
September 23, 2024 08:27 6m 22s master
master
September 23, 2024 08:27 6m 22s
llama : introduce anonymous namespace in llama.cpp Nix CI #10232: Pull request #9602 opened by danbev
September 23, 2024 08:00 17m 15s danbev:llama-namespace
danbev:llama-namespace
September 23, 2024 08:00 17m 15s
readme: Add offline-ai/cli programmable prompt engine language CLI for llama.cpp server Nix CI #10231: Pull request #9599 opened by snowyu
September 23, 2024 05:51 3m 28s snowyu:patch-readme-ppe
snowyu:patch-readme-ppe
September 23, 2024 05:51 3m 28s
threads: improve ggml_barrier scaling with large number of threads Nix CI #10230: Pull request #9598 synchronize by max-krasnyansky
September 23, 2024 04:49 6m 30s CodeLinaro:improve-ggml-barrier-scaling
CodeLinaro:improve-ggml-barrier-scaling
September 23, 2024 04:49 6m 30s
Revert "[SYCL] fallback mmvq (#9088)" (#9579) Nix CI #10229: Commit e62e978 pushed by airMeng
September 23, 2024 03:28 21m 25s master
master
September 23, 2024 03:28 21m 25s
vocab: refactor tokenizer to reduce the overhead of creating multi times tokenizer Nix CI #10228: Pull request #9449 synchronize by kylo5aby
September 23, 2024 02:27 6m 20s kylo5aby:refactor-tokenizer
kylo5aby:refactor-tokenizer
September 23, 2024 02:27 6m 20s
threads: improve ggml_barrier scaling with large number of threads Nix CI #10227: Pull request #9598 opened by max-krasnyansky
September 23, 2024 01:51 6m 27s CodeLinaro:improve-ggml-barrier-scaling
CodeLinaro:improve-ggml-barrier-scaling
September 23, 2024 01:51 6m 27s
musa: enable VMM support Nix CI #10226: Pull request #9597 opened by yeahdongcn
September 23, 2024 00:40 7m 19s makllama:musa_vmm
makllama:musa_vmm
September 23, 2024 00:40 7m 19s
Add basic function calling example using a llama-cli python wrapper Nix CI #10225: Pull request #9592 synchronize by dmahurin
September 22, 2024 21:13 6m 19s dmahurin:function-calling
dmahurin:function-calling
September 22, 2024 21:13 6m 19s
Add basic function calling example using a llama-cli python wrapper Nix CI #10224: Pull request #9592 synchronize by dmahurin
September 22, 2024 21:03 6m 16s dmahurin:function-calling
dmahurin:function-calling
September 22, 2024 21:03 6m 16s
perplexity : remove extra new lines after chunks Nix CI #10223: Pull request #9596 opened by ggerganov
September 22, 2024 19:27 17m 6s gg/perplexity-nl
gg/perplexity-nl
September 22, 2024 19:27 17m 6s
metal : use F32 prec for K*Q in vec FA Nix CI #10222: Pull request #9595 opened by ggerganov
September 22, 2024 19:21 6m 59s gg/metal-fa-f32-qk
gg/metal-fa-f32-qk
September 22, 2024 19:21 6m 59s
CUDA: Enable FP16_MMA for RDNA3 with rocWMMA (PoC) Nix CI #10221: Pull request #9594 opened by Nekotekina
September 22, 2024 17:03 Action required Nekotekina:rocwmma
Nekotekina:rocwmma
September 22, 2024 17:03 Action required
musa: enable building fat binaries, enable unified memory, and disabl… Nix CI #10220: Commit c35e586 pushed by slaren
September 22, 2024 14:55 32m 28s master
master
September 22, 2024 14:55 32m 28s
Add basic function calling example using a llama-cli python wrapper Nix CI #10219: Pull request #9592 opened by dmahurin
September 22, 2024 14:33 6m 22s dmahurin:function-calling
dmahurin:function-calling
September 22, 2024 14:33 6m 22s
Added link to Bielik model Nix CI #10218: Pull request #9591 opened by 32bitmicro
September 22, 2024 14:20 Action required LLaMANexus:master
LLaMANexus:master
September 22, 2024 14:20 Action required
Fix merge error in #9454 (#9589) Nix CI #10217: Commit 912c331 pushed by slaren
September 22, 2024 13:26 6m 22s master
master
September 22, 2024 13:26 6m 22s
ggml: RWKV_WKV: Fix merge error in #9454 Nix CI #10216: Pull request #9589 opened by MollySophia
September 22, 2024 12:57 6m 25s MollySophia:fix-error
MollySophia:fix-error
September 22, 2024 12:57 6m 25s
musa: enable building fat binaries, enable unified memory, and disable Flash Attention on QY1 (MTT S80) Nix CI #10215: Pull request #9526 synchronize by yeahdongcn
September 22, 2024 11:50 17m 5s makllama:upstream_master
makllama:upstream_master
September 22, 2024 11:50 17m 5s
CUDA: Enable K-shift operation for -ctk q8_0 (limited) Nix CI #10214: Pull request #9571 synchronize by Nekotekina
September 22, 2024 08:20 6m 26s Nekotekina:kshift
Nekotekina:kshift
September 22, 2024 08:20 6m 26s