Skip to content

Actions: huggingface/text-generation-inference

CI build

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
1,499 workflow runs
1,499 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Make handling of FP8 scales more consisent (#2666)
CI build #1569: Commit 5e0fb46 pushed by danieldk
October 19, 2024 07:05 54m 4s main
October 19, 2024 07:05 54m 4s
PR 2634 CI - Fix the tool_choice format for named choice by adapting OpenAIs scheme
CI build #1567: Pull request #2645 synchronize by drbh
October 18, 2024 16:12 6h 1m 19s pr-2634-ci-branch
October 18, 2024 16:12 6h 1m 19s
CI job. Gpt awq 4 (#2665)
CI build #1566: Commit 153ff37 pushed by Narsil
October 18, 2024 15:55 5h 25m 14s main
October 18, 2024 15:55 5h 25m 14s
CI job. Gpt awq 4
CI build #1565: Pull request #2665 synchronize by Narsil
October 18, 2024 15:55 5h 19m 39s gpt_awq_4
October 18, 2024 15:55 5h 19m 39s
Make handling of FP8 scales more consisent
CI build #1564: Pull request #2666 synchronize by danieldk
October 18, 2024 15:40 10m 48s maintenance/reciprocal-handling
October 18, 2024 15:40 10m 48s
PR 2634 CI - Fix the tool_choice format for named choice by adapting OpenAIs scheme
CI build #1563: Pull request #2645 synchronize by drbh
October 18, 2024 15:39 40m 53s pr-2634-ci-branch
October 18, 2024 15:39 40m 53s
Make handling of FP8 scales more consisent
CI build #1561: Pull request #2666 opened by danieldk
October 18, 2024 14:18 1h 22m 40s maintenance/reciprocal-handling
October 18, 2024 14:18 1h 22m 40s
CI job. Gpt awq 4
CI build #1560: Pull request #2665 synchronize by Narsil
October 18, 2024 12:42 3h 13m 31s gpt_awq_4
October 18, 2024 12:42 3h 13m 31s
CI job. Gpt awq 4
CI build #1559: Pull request #2665 synchronize by Narsil
October 18, 2024 11:03 1h 40m 6s gpt_awq_4
October 18, 2024 11:03 1h 40m 6s
CI job. Gpt awq 4
CI build #1558: Pull request #2665 synchronize by Narsil
October 18, 2024 10:29 43m 52s gpt_awq_4
October 18, 2024 10:29 43m 52s
CI job. Gpt awq 4
CI build #1557: Pull request #2665 synchronize by Narsil
October 18, 2024 10:22 7m 17s gpt_awq_4
October 18, 2024 10:22 7m 17s
CI job. Gpt awq 4
CI build #1556: Pull request #2665 synchronize by Narsil
October 18, 2024 10:14 23m 17s gpt_awq_4
October 18, 2024 10:14 23m 17s
CI job. Gpt awq 4
CI build #1555: Pull request #2665 opened by Narsil
October 18, 2024 10:02 12m 53s gpt_awq_4
October 18, 2024 10:02 12m 53s
Break cycle between the attention implementations and KV cache (#2627)
CI build #1554: Commit 8ec5755 pushed by danieldk
October 17, 2024 12:54 56m 46s main
October 17, 2024 12:54 56m 46s
fix: prefer inplace softmax to avoid copy (#2661)
CI build #1553: Commit 5f32dea pushed by drbh
October 17, 2024 12:49 58m 39s main
October 17, 2024 12:49 58m 39s
fix tgi-entrypoint wrapper in docker file: exec instead of spawning a…
CI build #1550: Commit 1b97e08 pushed by Narsil
October 17, 2024 09:15 55m 47s main
October 17, 2024 09:15 55m 47s
Fixing "deadlock" when python prompts for trust_remote_code by always
CI build #1549: Pull request #2664 opened by Narsil
October 17, 2024 09:04 1h 1m 23s fixup_tokenizer_trust
October 17, 2024 09:04 1h 1m 23s
Simplify the attention function (#2609)
CI build #1548: Commit 59ea38c pushed by Narsil
October 17, 2024 08:42 1h 7m 22s main
October 17, 2024 08:42 1h 7m 22s
Support e4m3fn KV cache (#2655)
CI build #1547: Commit 5bbe1ce pushed by Narsil
October 17, 2024 08:42 1h 3m 45s main
October 17, 2024 08:42 1h 3m 45s
Simplify the attention function
CI build #1546: Pull request #2609 synchronize by danieldk
October 17, 2024 08:04 1h 0m 49s maintenance/simplify-attention
October 17, 2024 08:04 1h 0m 49s