Skip to content

Actions: huggingface/text-generation-inference

Actions

All workflows

Actions

Loading...

Showing runs from all workflows
7,143 workflow runs
7,143 workflow runs
Event

Filter by event
Status

Filter by status
Branch
Actor

Filter by actor
Close stale issues and PRs Close stale issues and PRs #173: Scheduled
May 26, 2024 01:49 20s main
main
May 26, 2024 01:49 20s
Fix GPTQ for models which do not have float16 at the default dtype (simpler) Server Tests #1868: Pull request #1953 opened by danieldk
May 25, 2024 09:01 16m 47s bugfix/preserve-quantized-dtype-simpler
bugfix/preserve-quantized-dtype-simpler
May 25, 2024 09:01 16m 47s
Fix GPTQ for models which do not have float16 at the default dtype (simpler) Build and push docker image to internal registry #2610: Pull request #1953 opened by danieldk
May 25, 2024 09:01 1h 10m 52s bugfix/preserve-quantized-dtype-simpler
bugfix/preserve-quantized-dtype-simpler
May 25, 2024 09:01 1h 10m 52s
Fix GPTQ for models which do not have float16 at the default dtype (simpler) Automatic Documentation for Launcher #1151: Pull request #1953 opened by danieldk
May 25, 2024 09:01 1m 42s bugfix/preserve-quantized-dtype-simpler
bugfix/preserve-quantized-dtype-simpler
May 25, 2024 09:01 1m 42s
Fix GPTQ for models which do not have float16 at the default dtype Build and push docker image to internal registry #2609: Pull request #1951 synchronize by danieldk
May 25, 2024 08:53 41m 13s bugfix/preserve-quantized-dtype
bugfix/preserve-quantized-dtype
May 25, 2024 08:53 41m 13s
Fix GPTQ for models which do not have float16 at the default dtype Automatic Documentation for Launcher #1150: Pull request #1951 synchronize by danieldk
May 25, 2024 08:53 1m 30s bugfix/preserve-quantized-dtype
bugfix/preserve-quantized-dtype
May 25, 2024 08:53 1m 30s
Fix GPTQ for models which do not have float16 at the default dtype Server Tests #1867: Pull request #1951 synchronize by danieldk
May 25, 2024 08:53 10m 18s bugfix/preserve-quantized-dtype
bugfix/preserve-quantized-dtype
May 25, 2024 08:53 10m 18s
Fix GPTQ for models which do not have float16 at the default dtype Automatic Documentation for Launcher #1149: Pull request #1951 synchronize by danieldk
May 25, 2024 08:45 1m 41s bugfix/preserve-quantized-dtype
bugfix/preserve-quantized-dtype
May 25, 2024 08:45 1m 41s
Fix GPTQ for models which do not have float16 at the default dtype Build and push docker image to internal registry #2608: Pull request #1951 synchronize by danieldk
May 25, 2024 08:45 10m 31s bugfix/preserve-quantized-dtype
bugfix/preserve-quantized-dtype
May 25, 2024 08:45 10m 31s
Fix GPTQ for models which do not have float16 at the default dtype Server Tests #1866: Pull request #1951 synchronize by danieldk
May 25, 2024 08:45 8m 34s bugfix/preserve-quantized-dtype
bugfix/preserve-quantized-dtype
May 25, 2024 08:45 8m 34s
Close stale issues and PRs Close stale issues and PRs #172: Scheduled
May 25, 2024 01:46 17s main
main
May 25, 2024 01:46 17s
Fix GPTQ for models which do not have float16 at the default dtype Server Tests #1865: Pull request #1951 opened by danieldk
May 24, 2024 19:10 16m 55s bugfix/preserve-quantized-dtype
bugfix/preserve-quantized-dtype
May 24, 2024 19:10 16m 55s
Fix GPTQ for models which do not have float16 at the default dtype Build and push docker image to internal registry #2607: Pull request #1951 opened by danieldk
May 24, 2024 19:10 39m 0s bugfix/preserve-quantized-dtype
bugfix/preserve-quantized-dtype
May 24, 2024 19:10 39m 0s
Fix GPTQ for models which do not have float16 at the default dtype Automatic Documentation for Launcher #1148: Pull request #1951 opened by danieldk
May 24, 2024 19:10 1m 36s bugfix/preserve-quantized-dtype
bugfix/preserve-quantized-dtype
May 24, 2024 19:10 1m 36s
[Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. Server Tests #1864: Pull request #1940 synchronize by Narsil
May 24, 2024 16:10 12m 10s flashdecoding
flashdecoding
May 24, 2024 16:10 12m 10s
[Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. Build and push docker image to internal registry #2606: Pull request #1940 synchronize by Narsil
May 24, 2024 16:10 35m 25s flashdecoding
flashdecoding
May 24, 2024 16:10 35m 25s
[Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. Automatic Documentation for Launcher #1147: Pull request #1940 synchronize by Narsil
May 24, 2024 16:10 1m 41s flashdecoding
flashdecoding
May 24, 2024 16:10 1m 41s
Fix (flash) Gemma prefix and enable tests Automatic Documentation for Launcher #1146: Pull request #1950 opened by danieldk
May 24, 2024 15:37 1m 28s bugfix/gemma-prefix
bugfix/gemma-prefix
May 24, 2024 15:37 1m 28s
Fix (flash) Gemma prefix and enable tests Server Tests #1863: Pull request #1950 opened by danieldk
May 24, 2024 15:37 17m 22s bugfix/gemma-prefix
bugfix/gemma-prefix
May 24, 2024 15:37 17m 22s
Fix (flash) Gemma prefix and enable tests Build and push docker image to internal registry #2605: Pull request #1950 opened by danieldk
May 24, 2024 15:37 1h 58m 31s bugfix/gemma-prefix
bugfix/gemma-prefix
May 24, 2024 15:37 1h 58m 31s
[Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. Server Tests #1862: Pull request #1940 synchronize by Narsil
May 24, 2024 14:18 11m 57s flashdecoding
flashdecoding
May 24, 2024 14:18 11m 57s
[Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. Build and push docker image to internal registry #2604: Pull request #1940 synchronize by Narsil
May 24, 2024 14:18 2h 8m 32s flashdecoding
flashdecoding
May 24, 2024 14:18 2h 8m 32s
[Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. Automatic Documentation for Launcher #1145: Pull request #1940 synchronize by Narsil
May 24, 2024 14:18 1m 35s flashdecoding
flashdecoding
May 24, 2024 14:18 1m 35s
[Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. Server Tests #1861: Pull request #1940 synchronize by Narsil
May 24, 2024 14:16 2m 7s flashdecoding
flashdecoding
May 24, 2024 14:16 2m 7s
[Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. Build and push docker image to internal registry #2603: Pull request #1940 synchronize by Narsil
May 24, 2024 14:16 15m 42s flashdecoding
flashdecoding
May 24, 2024 14:16 15m 42s