Skip to content

Actions: huggingface/text-generation-inference

Actions

Server Tests

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
tests.yaml
2,366 workflow runs
2,366 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

PR 2634 CI - Fix the tool_choice format for named choice by adapting OpenAIs scheme Server Tests #3239: Pull request #2645 synchronize by drbh
October 20, 2024 21:57 8m 49s pr-2634-ci-branch
pr-2634-ci-branch
October 20, 2024 21:57 8m 49s
feat: return streaming errors as an event formatted for openai's client Server Tests #3238: Pull request #2668 opened by drbh
October 18, 2024 18:18 7m 21s return-streaming-error-in-openai-client-compatible-format
return-streaming-error-in-openai-client-compatible-format
October 18, 2024 18:18 7m 21s
PR 2634 CI - Fix the tool_choice format for named choice by adapting OpenAIs scheme Server Tests #3237: Pull request #2645 synchronize by drbh
October 18, 2024 16:12 6m 48s pr-2634-ci-branch
pr-2634-ci-branch
October 18, 2024 16:12 6m 48s
CI job. Gpt awq 4 Server Tests #3236: Pull request #2665 synchronize by Narsil
October 18, 2024 15:55 6m 45s gpt_awq_4
gpt_awq_4
October 18, 2024 15:55 6m 45s
Make handling of FP8 scales more consisent Server Tests #3235: Pull request #2666 synchronize by danieldk
October 18, 2024 15:40 7m 29s maintenance/reciprocal-handling
maintenance/reciprocal-handling
October 18, 2024 15:40 7m 29s
PR 2634 CI - Fix the tool_choice format for named choice by adapting OpenAIs scheme Server Tests #3234: Pull request #2645 synchronize by drbh
October 18, 2024 15:39 6m 55s pr-2634-ci-branch
pr-2634-ci-branch
October 18, 2024 15:39 6m 55s
PR 2634 CI - Fix the tool_choice format for named choice by adapting OpenAIs scheme Server Tests #3233: Pull request #2645 synchronize by drbh
October 18, 2024 15:36 2m 40s pr-2634-ci-branch
pr-2634-ci-branch
October 18, 2024 15:36 2m 40s
Make handling of FP8 scales more consisent Server Tests #3232: Pull request #2666 opened by danieldk
October 18, 2024 14:18 6m 44s maintenance/reciprocal-handling
maintenance/reciprocal-handling
October 18, 2024 14:18 6m 44s
CI job. Gpt awq 4 Server Tests #3231: Pull request #2665 synchronize by Narsil
October 18, 2024 12:42 7m 5s gpt_awq_4
gpt_awq_4
October 18, 2024 12:42 7m 5s
CI job. Gpt awq 4 Server Tests #3230: Pull request #2665 synchronize by Narsil
October 18, 2024 11:03 6m 32s gpt_awq_4
gpt_awq_4
October 18, 2024 11:03 6m 32s
CI job. Gpt awq 4 Server Tests #3229: Pull request #2665 synchronize by Narsil
October 18, 2024 10:29 6m 55s gpt_awq_4
gpt_awq_4
October 18, 2024 10:29 6m 55s
CI job. Gpt awq 4 Server Tests #3228: Pull request #2665 synchronize by Narsil
October 18, 2024 10:22 6m 25s gpt_awq_4
gpt_awq_4
October 18, 2024 10:22 6m 25s
CI job. Gpt awq 4 Server Tests #3227: Pull request #2665 synchronize by Narsil
October 18, 2024 10:14 6m 42s gpt_awq_4
gpt_awq_4
October 18, 2024 10:14 6m 42s
CI job. Gpt awq 4 Server Tests #3226: Pull request #2665 opened by Narsil
October 18, 2024 10:02 10m 14s gpt_awq_4
gpt_awq_4
October 18, 2024 10:02 10m 14s
fix: prefer inplace softmax to avoid copy Server Tests #3225: Pull request #2661 synchronize by drbh
October 17, 2024 12:48 8m 44s prefer-inplace-softmax-for-prefill-logprobs
prefer-inplace-softmax-for-prefill-logprobs
October 17, 2024 12:48 8m 44s
Break cycle between the attention implementations and KV cache Server Tests #3224: Pull request #2627 synchronize by danieldk
October 17, 2024 11:17 6m 35s maintenance/reshape-and-cache
maintenance/reshape-and-cache
October 17, 2024 11:17 6m 35s
Fixing "deadlock" when python prompts for trust_remote_code by always Server Tests #3223: Pull request #2664 opened by Narsil
October 17, 2024 09:04 7m 59s fixup_tokenizer_trust
fixup_tokenizer_trust
October 17, 2024 09:04 7m 59s
Simplify the attention function Server Tests #3222: Pull request #2609 synchronize by danieldk
October 17, 2024 08:04 12m 19s maintenance/simplify-attention
maintenance/simplify-attention
October 17, 2024 08:04 12m 19s
fix: prefer inplace softmax to avoid copy Server Tests #3221: Pull request #2661 opened by drbh
October 17, 2024 03:05 9m 31s prefer-inplace-softmax-for-prefill-logprobs
prefer-inplace-softmax-for-prefill-logprobs
October 17, 2024 03:05 9m 31s
Upgrade outlines to 0.1.1 Server Tests #3220: Pull request #2658 opened by aW3st
October 16, 2024 18:50 Action required aW3st:upgrade-outlines
aW3st:upgrade-outlines
October 16, 2024 18:50 Action required
We can have a tokenizer anywhere. Server Tests #3219: Pull request #2527 synchronize by Narsil
October 16, 2024 16:50 8m 40s omni_tokenizer
omni_tokenizer
October 16, 2024 16:50 8m 40s
Support e4m3fn KV cache Server Tests #3218: Pull request #2655 synchronize by danieldk
October 16, 2024 13:55 8m 40s feature/kv-cache-e4m3
feature/kv-cache-e4m3
October 16, 2024 13:55 8m 40s
Simplify the attention function Server Tests #3217: Pull request #2609 synchronize by danieldk
October 16, 2024 13:51 8m 40s maintenance/simplify-attention
maintenance/simplify-attention
October 16, 2024 13:51 8m 40s
PR 2634 CI - Fix the tool_choice format for named choice by adapting OpenAIs scheme Server Tests #3216: Pull request #2645 synchronize by drbh
October 16, 2024 13:49 9m 3s pr-2634-ci-branch
pr-2634-ci-branch
October 16, 2024 13:49 9m 3s
Simplify the attention function Server Tests #3215: Pull request #2609 synchronize by danieldk
October 16, 2024 13:12 9m 6s maintenance/simplify-attention
maintenance/simplify-attention
October 16, 2024 13:12 9m 6s