Skip to content

Actions: EricLBuehler/candle-vllm

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
288 workflow runs
288 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Support in-situ conversion of GPTQ model to marlin format (naive GPTQ…
Continuous integration #294: Commit 3ebf3b8 pushed by guoqingbao
October 21, 2024 10:24 1m 50s master
October 21, 2024 10:24 1m 50s
Support in-situ conversion of GPTQ model to marlin format (naive GPTQ kernel also supported).
Continuous integration #293: Pull request #92 opened by guoqingbao
October 21, 2024 10:21 1m 29s develop
October 21, 2024 10:21 1m 29s
Continuous integration
Continuous integration #292: Scheduled
October 21, 2024 01:05 1m 28s master
October 21, 2024 01:05 1m 28s
Add an example for marlin format conversion & update results (#91)
Continuous integration #291: Commit 46b10ad pushed by guoqingbao
October 16, 2024 09:48 1m 53s master
October 16, 2024 09:48 1m 53s
Add an example for marlin format conversion & update results
Continuous integration #290: Pull request #91 synchronize by guoqingbao
October 16, 2024 09:46 2m 4s develop
October 16, 2024 09:46 2m 4s
Add an example for marlin format conversion & update results
Continuous integration #289: Pull request #91 opened by guoqingbao
October 16, 2024 09:45 2m 9s develop
October 16, 2024 09:45 2m 9s
Update Demo video
Continuous integration #288: Commit 885ee3e pushed by guoqingbao
October 15, 2024 09:10 1m 40s master
October 15, 2024 09:10 1m 40s
Support bf16 inputs for GPTQ/Marlin format quantization (#90)
Continuous integration #287: Commit e62b7e1 pushed by guoqingbao
October 15, 2024 07:49 1m 44s master
October 15, 2024 07:49 1m 44s
Support bf16 inputs for GPTQ/Marlin format quantization
Continuous integration #286: Pull request #90 synchronize by guoqingbao
October 15, 2024 07:47 2m 24s develop
October 15, 2024 07:47 2m 24s
Support GPTQ/Marlin format quantization (4bit weight, f16 input) (#89)
Continuous integration #285: Commit 1b4b0d4 pushed by guoqingbao
October 14, 2024 10:43 2m 12s master
October 14, 2024 10:43 2m 12s
Support GPTQ/Marlin format quantization (4bit weight, f16 input)
Continuous integration #284: Pull request #89 synchronize by guoqingbao
October 14, 2024 10:42 2m 22s develop
October 14, 2024 10:42 2m 22s
Continuous integration
Continuous integration #283: Scheduled
October 14, 2024 01:04 1m 9s master
October 14, 2024 01:04 1m 9s
Continuous integration
Continuous integration #282: Scheduled
October 7, 2024 01:05 1m 4s master
October 7, 2024 01:05 1m 4s
Continuous integration
Continuous integration #281: Scheduled
September 30, 2024 01:05 1m 22s master
September 30, 2024 01:05 1m 22s
Continuous integration
Continuous integration #280: Scheduled
September 23, 2024 01:02 1m 57s master
September 23, 2024 01:02 1m 57s
Continuous integration
Continuous integration #279: Scheduled
September 16, 2024 01:03 1m 39s master
September 16, 2024 01:03 1m 39s
Continuous integration
Continuous integration #278: Scheduled
September 9, 2024 01:01 1m 42s master
September 9, 2024 01:01 1m 42s
Continuous integration
Continuous integration #277: Scheduled
September 2, 2024 01:00 1m 21s master
September 2, 2024 01:00 1m 21s
Continuous integration
Continuous integration #276: Scheduled
August 26, 2024 00:57 1m 18s master
August 26, 2024 00:57 1m 18s
Custom benchmark with parameters (#88)
Continuous integration #275: Commit c7ff257 pushed by guoqingbao
August 23, 2024 09:09 1m 9s master
August 23, 2024 09:09 1m 9s
Custom benchmark with parameters
Continuous integration #274: Pull request #88 opened by guoqingbao
August 23, 2024 09:08 1m 5s develop
August 23, 2024 09:08 1m 5s
Fix Gemma-2 multiple eos/bos ids (#87)
Continuous integration #273: Commit 124fadc pushed by guoqingbao
August 22, 2024 02:30 1m 26s master
August 22, 2024 02:30 1m 26s
Fix Gemma-2 multiple eos/bos ids
Continuous integration #272: Pull request #87 opened by guoqingbao
August 22, 2024 02:28 1m 32s develop
August 22, 2024 02:28 1m 32s
Support softcapping (Gemma-2 models) (#86)
Continuous integration #271: Commit c170b23 pushed by guoqingbao
August 21, 2024 10:25 1m 18s master
August 21, 2024 10:25 1m 18s
Support softcapping (Gemma-2 models)
Continuous integration #270: Pull request #86 synchronize by guoqingbao
August 21, 2024 10:24 1m 39s develop
August 21, 2024 10:24 1m 39s