Skip to content

Actions: EricLBuehler/candle-vllm

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
325 workflow runs
325 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix corner case when block table too small
Continuous integration #205: Pull request #56 synchronize by EricLBuehler
July 12, 2024 02:07 1m 11s fix_block_table_too_small
July 12, 2024 02:07 1m 11s
Fix corner case when block table too small
Continuous integration #204: Pull request #56 synchronize by EricLBuehler
July 12, 2024 02:05 1m 11s fix_block_table_too_small
July 12, 2024 02:05 1m 11s
Fix corner case when block table too small
Continuous integration #203: Pull request #56 opened by EricLBuehler
July 12, 2024 00:46 2m 40s fix_block_table_too_small
July 12, 2024 00:46 2m 40s
Merge pull request #55 from EricLBuehler/develop
Continuous integration #202: Commit d0f31eb pushed by guoqingbao
July 11, 2024 11:41 1m 10s master
July 11, 2024 11:41 1m 10s
Fix mistral output repetition with F32 rope and penalty & temperature parameters
Continuous integration #201: Pull request #55 opened by guoqingbao
July 11, 2024 11:41 1m 32s develop
July 11, 2024 11:41 1m 32s
Merge pull request #54 from EricLBuehler/develop
Continuous integration #200: Commit bfa16e3 pushed by guoqingbao
July 11, 2024 10:51 1m 11s master
July 11, 2024 10:51 1m 11s
Fix mistral model & more optional model-specific parameters.
Continuous integration #199: Pull request #54 synchronize by guoqingbao
July 11, 2024 10:49 2m 35s develop
July 11, 2024 10:49 2m 35s
Fix mistral model & more optional model-specific parameters.
Continuous integration #198: Pull request #54 synchronize by guoqingbao
July 11, 2024 10:45 1m 39s develop
July 11, 2024 10:45 1m 39s
Support Phi2 and Mistral models, fix generation remainder, more sampl…
Continuous integration #197: Commit 5d62054 pushed by EricLBuehler
July 11, 2024 10:11 1m 24s master
July 11, 2024 10:11 1m 24s
Support Phi2 and Mistral models, fix generation remainder, more sampling parameters, etc.
Continuous integration #196: Pull request #53 opened by guoqingbao
July 11, 2024 09:47 2m 34s develop
July 11, 2024 09:47 2m 34s
Merge pull request #52 from EricLBuehler/develop
Continuous integration #195: Commit 8552167 pushed by guoqingbao
July 9, 2024 03:03 2m 7s master
July 9, 2024 03:03 2m 7s
Fix bug for previous removal of repeat_kv (when key_value_heads > 1 and < attention_heads)
Continuous integration #194: Pull request #52 opened by guoqingbao
July 9, 2024 03:00 2m 27s develop
July 9, 2024 03:00 2m 27s
Qwen model default 1.8B
Continuous integration #193: Commit f16e7a5 pushed by guoqingbao
July 8, 2024 15:39 2m 38s master
July 8, 2024 15:39 2m 38s
Update README.md
Continuous integration #192: Commit a77ac8c pushed by guoqingbao
July 8, 2024 12:36 1m 52s master
July 8, 2024 12:36 1m 52s
Merge pull request #50 from EricLBuehler/develop
Continuous integration #191: Commit d53fc99 pushed by guoqingbao
July 8, 2024 11:10 1m 36s master
July 8, 2024 11:10 1m 36s
Higher precision for rope in Gemma model.
Continuous integration #190: Pull request #50 opened by guoqingbao
July 8, 2024 11:00 1m 29s develop
July 8, 2024 11:00 1m 29s
Merge pull request #49 from EricLBuehler/develop
Continuous integration #189: Commit 601b7db pushed by guoqingbao
July 8, 2024 09:27 1m 17s master
July 8, 2024 09:27 1m 17s
Support Gemma model & remove repeat_kv (replaced with broadcast matmu…
Continuous integration #188: Pull request #49 opened by guoqingbao
July 8, 2024 09:23 2m 37s develop
July 8, 2024 09:23 2m 37s
Merge pull request #48 from EricLBuehler/develop
Continuous integration #187: Commit 5e806a0 pushed by guoqingbao
July 8, 2024 04:19 2m 8s master
July 8, 2024 04:19 2m 8s
Error prompt for requested message exceeds model capacity
Continuous integration #186: Pull request #48 opened by guoqingbao
July 8, 2024 04:15 2m 15s develop
July 8, 2024 04:15 2m 15s
Continuous integration
Continuous integration #185: Scheduled
July 8, 2024 00:56 1m 46s master
July 8, 2024 00:56 1m 46s
Support qwen2 model, optimize phi3 model, revise model loading strate…
Continuous integration #184: Commit 211346e pushed by EricLBuehler
July 5, 2024 08:52 1m 11s master
July 5, 2024 08:52 1m 11s
Support qwen2 model, optimize phi3 model, revise model loading strategy
Continuous integration #183: Pull request #46 synchronize by guoqingbao
July 5, 2024 07:21 1m 45s guoqingbao:merge
July 5, 2024 07:21 1m 45s
Support qwen2 model, optimize phi3 model, revise model loading strategy
Continuous integration #182: Pull request #46 synchronize by guoqingbao
July 4, 2024 10:27 2m 12s guoqingbao:merge
July 4, 2024 10:27 2m 12s
Support qwen2 model, optimize phi3 model, revise model loading strategy
Continuous integration #181: Pull request #46 synchronize by guoqingbao
July 4, 2024 10:01 2m 7s guoqingbao:merge
July 4, 2024 10:01 2m 7s