Skip to content

Actions: predibase/lorax

Server Tests

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
701 workflow runs
701 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix compile for qwen-2.5-32b
Server Tests #560: Pull request #645 opened by tgaddair
October 16, 2024 16:43 4m 52s plumb-token
October 16, 2024 16:43 4m 52s
Fix llava_next for llama 3.2 vision cross attention states
Server Tests #559: Pull request #641 opened by tgaddair
October 15, 2024 17:56 4m 18s fix-llava
October 15, 2024 17:56 4m 18s
Return n choices for chat completions API
Server Tests #558: Pull request #638 synchronize by tgaddair
October 15, 2024 16:45 9m 7s return-n
October 15, 2024 16:45 9m 7s
Look for language model lm head
Server Tests #557: Pull request #640 opened by Infernaught
October 15, 2024 16:44 4m 26s fix_vlm_inference
October 15, 2024 16:44 4m 26s
Return n choices for chat completions API
Server Tests #556: Pull request #638 synchronize by tgaddair
October 15, 2024 15:53 4m 32s return-n
October 15, 2024 15:53 4m 32s
Return n choices for chat completions API
Server Tests #555: Pull request #638 synchronize by tgaddair
October 15, 2024 04:36 4m 17s return-n
October 15, 2024 04:36 4m 17s
Add --disable-sgmv flag
Server Tests #554: Pull request #639 synchronize by joseph-predibase
October 15, 2024 03:14 4m 25s joseph/disable_sgmv
October 15, 2024 03:14 4m 25s
Add --disable-sgmv flag
Server Tests #553: Pull request #639 synchronize by joseph-predibase
October 15, 2024 03:03 4m 32s joseph/disable_sgmv
October 15, 2024 03:03 4m 32s
Add --disable-sgmv flag
Server Tests #552: Pull request #639 synchronize by joseph-predibase
October 15, 2024 00:01 4m 34s joseph/disable_sgmv
October 15, 2024 00:01 4m 34s
Return n choices for chat completions API
Server Tests #551: Pull request #638 synchronize by tgaddair
October 14, 2024 04:41 4m 17s return-n
October 14, 2024 04:41 4m 17s
Fix cuda graph tracing without lora ranks
Server Tests #550: Pull request #634 opened by tgaddair
October 7, 2024 17:53 4m 9s fix-graph-ranks
October 7, 2024 17:53 4m 9s
Fix FlashInfer when not using prefix caching
Server Tests #549: Pull request #633 synchronize by tgaddair
October 4, 2024 21:50 3m 47s fix-flashinfer-graph
October 4, 2024 21:50 3m 47s
Fix FlashInfer when not using prefix caching
Server Tests #548: Pull request #633 opened by tgaddair
October 4, 2024 21:43 4m 21s fix-flashinfer-graph
October 4, 2024 21:43 4m 21s
Fix punica kernel compilation
Server Tests #547: Pull request #632 synchronize by tgaddair
October 4, 2024 18:14 3m 52s fix-kernels
October 4, 2024 18:14 3m 52s
Fix punica kernel compilation
Server Tests #546: Pull request #632 opened by tgaddair
October 4, 2024 18:03 4m 19s fix-kernels
October 4, 2024 18:03 4m 19s
Fix prefix plumbing and BGMV compiler dimensions
Server Tests #545: Pull request #631 synchronize by tgaddair
October 3, 2024 23:49 4m 36s fix-prefix
October 3, 2024 23:49 4m 36s
Fix prefix plumbing and BGMV compiler dimensions
Server Tests #544: Pull request #631 opened by tgaddair
October 3, 2024 23:48 20s fix-prefix
October 3, 2024 23:48 20s
Merge weights
Server Tests #543: Pull request #600 synchronize by tgaddair
October 3, 2024 16:53 4m 37s merge-weights
October 3, 2024 16:53 4m 37s
Merge weights
Server Tests #542: Pull request #600 synchronize by tgaddair
October 3, 2024 16:34 3m 59s merge-weights
October 3, 2024 16:34 3m 59s
Added ranks 96 and 128 to BGMV kernel
Server Tests #541: Pull request #630 opened by tgaddair
October 3, 2024 16:18 4m 24s bgmv-128
October 3, 2024 16:18 4m 24s
Fix retrace message
Server Tests #540: Pull request #629 opened by tgaddair
October 2, 2024 23:48 3m 56s fix-warning
October 2, 2024 23:48 3m 56s
Fix CUDA graphs for Medusa
Server Tests #539: Pull request #628 synchronize by tgaddair
October 2, 2024 23:32 4m 17s fix-compile-medusa
October 2, 2024 23:32 4m 17s
Fix CUDA graphs for Medusa
Server Tests #538: Pull request #628 opened by tgaddair
October 2, 2024 23:31 18s fix-compile-medusa
October 2, 2024 23:31 18s
Fix CUDA graph compilation
Server Tests #537: Pull request #627 synchronize by tgaddair
October 2, 2024 22:17 4m 17s fix-compile
October 2, 2024 22:17 4m 17s
Fix CUDA graph compilation
Server Tests #536: Pull request #627 opened by tgaddair
October 2, 2024 22:16 15s fix-compile
October 2, 2024 22:16 15s