-
Notifications
You must be signed in to change notification settings - Fork 1.2k
Comparing changes
Open a pull request
base repository: huggingface/text-generation-inference
base: v3.3.0
head repository: huggingface/text-generation-inference
compare: v3.3.1
- 12 commits
- 96 files changed
- 6 contributors
Commits on May 10, 2025
-
Change HPU warmup logic: seq length should be with exponential growth (…
…#3217) Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com> Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for c94f415 - Browse repository at this point
Copy the full SHA c94f415View commit details
Commits on May 12, 2025
-
Adjust the
round_up_seq
logic in Gaudi backend (#3224)Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 535ce23 - Browse repository at this point
Copy the full SHA 535ce23View commit details
Commits on May 15, 2025
-
* Update to Torch 2.7.0 * Try to fix typer/click issue * Pin click to fix incompatibility with typer * Fix some test outputs with slight deviations * Attempt again to sync with CI * Mamba too * Fixup mllama Also switch to `unsloth/Llama-3.2-11B-Vision-Instruct` for testing from the EU :).
Configuration menu - View commit details
-
Copy full SHA for 7e531f4 - Browse repository at this point
Copy the full SHA 7e531f4View commit details -
Enable Llama4 for Gaudi backend (#3223)
Signed-off-by: yuanwu <yuan.wu@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 18cbecf - Browse repository at this point
Copy the full SHA 18cbecfView commit details
Commits on May 16, 2025
-
Configuration menu - View commit details
-
Copy full SHA for 58934c8 - Browse repository at this point
Copy the full SHA 58934c8View commit details
Commits on May 19, 2025
-
Deepseek R1 for Gaudi backend (#3211)
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for d658b5d - Browse repository at this point
Copy the full SHA d658b5dView commit details
Commits on May 20, 2025
-
Refine warmup and upgrade to synapse AI 1.21.0 (#3234)
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 000e313 - Browse repository at this point
Copy the full SHA 000e313View commit details -
Fix the crash in default ATTENTION path for Gaudi backend (#3235)
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 43b1b07 - Browse repository at this point
Copy the full SHA 43b1b07View commit details
Commits on May 21, 2025
-
Switch to punica-sgmv kernel from the Hub (#3236)
* Switch to punica-sgmv kernel from the Hub This also switches (temporarily) to the tgi-nix/kernel-builder merge branch, bumping up to CUDA 12.8 (same as non-Nix Torch). * nix: client depends on aiohttp This probably worked before the nixpkgs bump because a dependency propagated aiohttp.
Configuration menu - View commit details
-
Copy full SHA for e325287 - Browse repository at this point
Copy the full SHA e325287View commit details
Commits on May 22, 2025
-
Move input_ids to hpu and remove disposal of adapter_meta (#3237)
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 9e7e546 - Browse repository at this point
Copy the full SHA 9e7e546View commit details -
Configuration menu - View commit details
-
Copy full SHA for 674c514 - Browse repository at this point
Copy the full SHA 674c514View commit details -
Configuration menu - View commit details
-
Copy full SHA for 767a652 - Browse repository at this point
Copy the full SHA 767a652View commit details
This comparison is taking too long to generate.
Unfortunately it looks like we can’t render this comparison for you right now. It might be too big, or there might be something weird with your repository.
You can try running this command locally to see the comparison on your machine:
git diff v3.3.0...v3.3.1