Skip to content

Actions: huggingface/text-generation-inference

Build documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
55 workflow runs
55 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix: docs typo (#2777)
Build documentation #55: Commit caff779 pushed by danieldk
November 26, 2024 13:29 51s main
November 26, 2024 13:29 51s
chore: prepare 2.4.1 release (#2773)
Build documentation #54: Commit 780531e pushed by OlivierDehaene
November 22, 2024 17:26 41s main
November 22, 2024 17:26 41s
feat: add payload limit (#2726)
Build documentation #53: Commit ab7ccf5 pushed by OlivierDehaene
November 21, 2024 18:20 44s main
November 21, 2024 18:20 44s
PR 2634 CI - Fix the tool_choice format for named choice by adapting …
Build documentation #52: Commit 5489406 pushed by drbh
November 19, 2024 18:32 41s main
November 19, 2024 18:32 41s
Add initial support for compressed-tensors checkpoints (#2732)
Build documentation #51: Commit a785000 pushed by danieldk
November 10, 2024 12:54 38s main
November 10, 2024 12:54 38s
Support qwen2 vl (#2689)
Build documentation #50: Commit befd9f6 pushed by drbh
October 30, 2024 16:40 38s main
October 30, 2024 16:40 38s
Choosing input/total tokens automatically based on available VRAM? (#…
Build documentation #49: Commit 0c9b6cd pushed by Narsil
October 28, 2024 03:59 39s main
October 28, 2024 03:59 39s
chore: prepare 2.4.0 release (#2695)
Build documentation #48: Commit a6b02da pushed by OlivierDehaene
October 25, 2024 21:10 38s main
October 25, 2024 21:10 38s
feat: allow any supported payload on /invocations (#2683)
Build documentation #47: Commit 41c2623 pushed by OlivierDehaene
October 23, 2024 11:26 39s main
October 23, 2024 11:26 39s
feat: natively support Granite models (#2682)
Build documentation #46: Commit 03c9388 pushed by OlivierDehaene
October 23, 2024 10:04 43s main
October 23, 2024 10:04 43s
Support e4m3fn KV cache (#2655)
Build documentation #45: Commit 5bbe1ce pushed by Narsil
October 17, 2024 08:42 50s main
October 17, 2024 08:42 50s
Clarify gated description and quicktour (#2631)
Build documentation #44: Commit 51f5401 pushed by Narsil
October 14, 2024 14:31 46s main
October 14, 2024 14:31 46s
Small fixes for supported models (#2471)
Build documentation #43: Commit ce28ee8 pushed by Narsil
October 14, 2024 13:26 42s main
October 14, 2024 13:26 42s
Update documentation to most recent stable version of TGI. (#2625)
Build documentation #42: Commit d912f0b pushed by Narsil
October 10, 2024 14:00 17s main
October 10, 2024 14:00 17s
Add basic FP8 KV cache support (#2603)
Build documentation #41: Commit 2358c2b pushed by danieldk
October 4, 2024 15:51 57s main
October 4, 2024 15:51 57s
Revert "Unroll notify error into generate response" (#2605)
Build documentation #40: Commit 3011639 pushed by drbh
October 3, 2024 21:56 45s main
October 3, 2024 21:56 45s
New release 2.3.1 (#2604)
Build documentation #39: Commit f6e2f05 pushed by Narsil
October 3, 2024 12:43 44s main
October 3, 2024 12:43 44s
Unroll notify error into generate response (#2597)
Build documentation #38: Commit d22b0c1 pushed by drbh
October 2, 2024 15:35 44s main
October 2, 2024 15:35 44s
CI (2592): Allow LoRA adapter revision in server launcher (#2602)
Build documentation #37: Commit 2335459 pushed by drbh
October 2, 2024 14:51 43s main
October 2, 2024 14:51 43s
Mllama flash version (#2585)
Build documentation #36: Commit d18ed5c pushed by Narsil
October 2, 2024 09:22 38s main
October 2, 2024 09:22 38s
feat: support phi3.5 moe (#2479)
Build documentation #35: Commit 93a7042 pushed by danieldk
September 30, 2024 09:15 40s main
September 30, 2024 09:15 40s
Update ROCM libs and improvements (#2579)
Build documentation #34: Commit f9e561e pushed by danieldk
September 30, 2024 08:54 45s main
September 30, 2024 08:54 45s
Update architecture.md (#2577)
Build documentation #33: Commit e790cfc pushed by danieldk
September 30, 2024 06:56 44s main
September 30, 2024 06:56 44s
remove LORA_ADAPTERS_PATH (#2563)
Build documentation #32: Commit 7efcb5e pushed by Narsil
September 24, 2024 23:20 48s main
September 24, 2024 23:20 48s
Adding note for private models in quick-tour document (#2548)
Build documentation #31: Commit e6d2965 pushed by Narsil
September 24, 2024 13:06 45s main
September 24, 2024 13:06 45s