Skip to content

Actions: huggingface/text-generation-inference

Actions

Automatic Documentation for Launcher

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
autodocs.yaml
1,521 workflow run results
1,521 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

chore: prepare 2.4.0 release Automatic Documentation for Launcher #1615: Pull request #2695 opened by OlivierDehaene
October 25, 2024 20:41 6m 53s chore/prepare_2.4
chore/prepare_2.4
October 25, 2024 20:41 6m 53s
feat: add triton kernels to decrease latency of large batches Automatic Documentation for Launcher #1614: Pull request #2687 synchronize by OlivierDehaene
October 25, 2024 20:14 7m 3s feat/triton_prepare
feat/triton_prepare
October 25, 2024 20:14 7m 3s
feat: add triton kernels to decrease latency of large batches Automatic Documentation for Launcher #1613: Pull request #2687 synchronize by OlivierDehaene
October 25, 2024 19:13 7m 0s feat/triton_prepare
feat/triton_prepare
October 25, 2024 19:13 7m 0s
feat: return streaming errors as an event formatted for openai's client Automatic Documentation for Launcher #1612: Pull request #2668 synchronize by drbh
October 25, 2024 15:57 7m 24s return-streaming-error-in-openai-client-compatible-format
return-streaming-error-in-openai-client-compatible-format
October 25, 2024 15:57 7m 24s
feat: return streaming errors as an event formatted for openai's client Automatic Documentation for Launcher #1610: Pull request #2668 synchronize by drbh
October 25, 2024 14:35 6m 54s return-streaming-error-in-openai-client-compatible-format
return-streaming-error-in-openai-client-compatible-format
October 25, 2024 14:35 6m 54s
Avoiding timeout for bloom tests. Automatic Documentation for Launcher #1609: Pull request #2693 synchronize by Narsil
October 25, 2024 14:16 7m 5s avoid_timeout
avoid_timeout
October 25, 2024 14:16 7m 5s
Switch from fbgemm-gpu w8a8 scaled matmul to vLLM/marlin-kernels Automatic Documentation for Launcher #1607: Pull request #2688 synchronize by danieldk
October 25, 2024 10:09 6m 59s feature/cc89-cutlass-w8a8
feature/cc89-cutlass-w8a8
October 25, 2024 10:09 6m 59s
Avoiding timeout for bloom tests. Automatic Documentation for Launcher #1606: Pull request #2693 synchronize by Narsil
October 25, 2024 09:46 6m 43s avoid_timeout
avoid_timeout
October 25, 2024 09:46 6m 43s
feat: add triton kernels to decrease latency of large batches Automatic Documentation for Launcher #1605: Pull request #2687 synchronize by OlivierDehaene
October 25, 2024 09:34 7m 22s feat/triton_prepare
feat/triton_prepare
October 25, 2024 09:34 7m 22s
Avoiding timeout for bloom tests. Automatic Documentation for Launcher #1604: Pull request #2693 synchronize by Narsil
October 25, 2024 09:26 6m 53s avoid_timeout
avoid_timeout
October 25, 2024 09:26 6m 53s
Avoiding timeout for bloom tests. Automatic Documentation for Launcher #1603: Pull request #2693 synchronize by Narsil
October 25, 2024 09:00 6m 49s avoid_timeout
avoid_timeout
October 25, 2024 09:00 6m 49s
Upgrade outlines to 0.1.1 Automatic Documentation for Launcher #1602: Pull request #2690 synchronize by Narsil
October 25, 2024 08:49 6m 58s upgrade-outlines
upgrade-outlines
October 25, 2024 08:49 6m 58s
feat: add triton kernels to decrease latency of large batches Automatic Documentation for Launcher #1601: Pull request #2687 synchronize by OlivierDehaene
October 25, 2024 08:43 6m 56s feat/triton_prepare
feat/triton_prepare
October 25, 2024 08:43 6m 56s
feat: add triton kernels to decrease latency of large batches Automatic Documentation for Launcher #1600: Pull request #2687 synchronize by OlivierDehaene
October 25, 2024 08:37 7m 5s feat/triton_prepare
feat/triton_prepare
October 25, 2024 08:37 7m 5s
Add support for stop words in TRTLLM Automatic Documentation for Launcher #1599: Pull request #2678 synchronize by Narsil
October 25, 2024 08:21 7m 5s trtllm-stop-words
trtllm-stop-words
October 25, 2024 08:21 7m 5s
Choosing input/total tokens automatically based on available VRAM? Automatic Documentation for Launcher #1598: Pull request #2673 synchronize by Narsil
October 25, 2024 08:20 7m 32s auto_length
auto_length
October 25, 2024 08:20 7m 32s
We can have a tokenizer anywhere. Automatic Documentation for Launcher #1597: Pull request #2527 synchronize by Narsil
October 25, 2024 07:59 7m 8s omni_tokenizer
omni_tokenizer
October 25, 2024 07:59 7m 8s
Avoiding timeout for bloom tests. Automatic Documentation for Launcher #1596: Pull request #2693 opened by Narsil
October 25, 2024 07:50 7m 7s avoid_timeout
avoid_timeout
October 25, 2024 07:50 7m 7s
Fixing mt0 test. Automatic Documentation for Launcher #1595: Pull request #2692 opened by Narsil
October 25, 2024 07:34 7m 6s update_mt0_test
update_mt0_test
October 25, 2024 07:34 7m 6s
Fixing rocm gptq by using triton code too (renamed cuda into triton). Automatic Documentation for Launcher #1594: Pull request #2691 opened by Narsil
October 25, 2024 05:27 6m 54s fix_rocm_ci
fix_rocm_ci
October 25, 2024 05:27 6m 54s
We can have a tokenizer anywhere. Automatic Documentation for Launcher #1593: Pull request #2527 synchronize by Narsil
October 25, 2024 05:23 5m 47s omni_tokenizer
omni_tokenizer
October 25, 2024 05:23 5m 47s
[TENSORRT-LLM] - Implement new looper thread based backend Automatic Documentation for Launcher #1592: Pull request #2357 synchronize by Narsil
October 25, 2024 05:16 6m 57s trtllm-executor-thread
trtllm-executor-thread
October 25, 2024 05:16 6m 57s
[TENSORRT-LLM] - Implement new looper thread based backend Automatic Documentation for Launcher #1591: Pull request #2357 synchronize by Narsil
October 25, 2024 05:10 7m 18s trtllm-executor-thread
trtllm-executor-thread
October 25, 2024 05:10 7m 18s
[TENSORRT-LLM] - Implement new looper thread based backend Automatic Documentation for Launcher #1590: Pull request #2357 synchronize by Narsil
October 25, 2024 05:06 7m 2s trtllm-executor-thread
trtllm-executor-thread
October 25, 2024 05:06 7m 2s
Upgrade outlines to 0.1.1 Automatic Documentation for Launcher #1589: Pull request #2690 opened by Narsil
October 25, 2024 04:53 7m 7s upgrade-outlines
upgrade-outlines
October 25, 2024 04:53 7m 7s