Skip to content

Actions: PygmalionAI/aphrodite-engine

ruff

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
1,303 workflow runs
1,303 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

quantization: update marlin to use AphroditeParameters
ruff #1315: Pull request #913 opened by AlpinDale
December 18, 2024 13:36 32s marlin-params
December 18, 2024 13:36 32s
fix: empty prompt crashing the server (#912)
ruff #1314: Commit 16e5b2b pushed by AlpinDale
December 18, 2024 13:28 35s main
December 18, 2024 13:28 35s
fix: empty prompt crashing the server
ruff #1313: Pull request #912 opened by AlpinDale
December 18, 2024 13:27 28s empty-prompt-crash
December 18, 2024 13:27 28s
xpu: refactor the model runner for tensor parallelism (#910)
ruff #1312: Commit 673621a pushed by AlpinDale
December 17, 2024 02:50 18s main
December 17, 2024 02:50 18s
xpu: refactor the model runner for tensor parallelism
ruff #1311: Pull request #910 opened by AlpinDale
December 17, 2024 02:50 21s xpu-tp
December 17, 2024 02:50 21s
feat: support finetuned lm_head and embed_tokens in LoRA adapters
ruff #1310: Pull request #909 opened by AlpinDale
December 17, 2024 02:09 20s lm_head_lora
December 17, 2024 02:09 20s
Reduce peak memory for prompt_logprobs requests
ruff #1309: Pull request #907 opened by 50h100a
December 16, 2024 20:12 22s prompt_logprobs_mem
December 16, 2024 20:12 22s
ray: better error when placement group topology is incorrect (#906)
ruff #1308: Commit d69273b pushed by AlpinDale
December 16, 2024 03:38 24s main
December 16, 2024 03:38 24s
ray: better error when placement group topology is incorrect
ruff #1307: Pull request #906 opened by AlpinDale
December 16, 2024 03:37 20s ray-bad-topology
December 16, 2024 03:37 20s
December 16, 2024 03:15 19s
spec decode: fix logprobs when using speculative decoding (#904)
ruff #1304: Commit ab533e0 pushed by AlpinDale
December 16, 2024 03:04 21s main
December 16, 2024 03:04 21s
Revert "feat: add support for chunked prefill + prefix caching (#871)"
ruff #1302: Pull request #903 opened by AlpinDale
December 16, 2024 02:53 21s revert_871
December 16, 2024 02:53 21s
chore: add AphroditeParameter support for FP8 quant (#902)
ruff #1301: Commit afc9a28 pushed by AlpinDale
December 16, 2024 02:52 19s main
December 16, 2024 02:52 19s
chore: add AphroditeParameter support for FP8 quant
ruff #1300: Pull request #902 opened by AlpinDale
December 16, 2024 02:51 24s fp8-parameter
December 16, 2024 02:51 24s
kernel: do not compile machete for cuda 11 and below (#901)
ruff #1299: Commit 2a60b8f pushed by AlpinDale
December 16, 2024 02:41 18s main
December 16, 2024 02:41 18s
kernel: do not compile machete for cuda 11 and below
ruff #1298: Pull request #901 opened by AlpinDale
December 16, 2024 02:40 20s machete_cu11
December 16, 2024 02:40 20s
fix: ShardedStateLoader with fp8 quant (#900)
ruff #1297: Commit 64c05b9 pushed by AlpinDale
December 16, 2024 02:31 19s main
December 16, 2024 02:31 19s
fix: ShardedStateLoader with fp8 quant
ruff #1296: Pull request #900 opened by AlpinDale
December 16, 2024 02:31 25s sharded-fp8
December 16, 2024 02:31 25s
spec decode: add support for EAGLE (#899)
ruff #1295: Commit 132aa2a pushed by AlpinDale
December 16, 2024 02:28 19s main
December 16, 2024 02:28 19s
spec decode: add support for EAGLE
ruff #1294: Pull request #899 opened by AlpinDale
December 16, 2024 02:27 19s eagle
December 16, 2024 02:27 19s
feat: add torch.compile for GemmaRMSNorm (#898)
ruff #1293: Commit bfc3da4 pushed by AlpinDale
December 16, 2024 01:05 23s main
December 16, 2024 01:05 23s
feat: add torch.compile for GemmaRMSNorm
ruff #1292: Pull request #898 opened by AlpinDale
December 16, 2024 00:58 27s gemma-rms
December 16, 2024 00:58 27s
api: add client timeouts for the ZeroMQ server (#897)
ruff #1291: Commit a00ab49 pushed by AlpinDale
December 16, 2024 00:54 22s main
December 16, 2024 00:54 22s