Skip to content

Pull requests: huggingface/text-generation-inference

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

[gaudi] Deepseek v2 mla and add ep to unquantized moe
#3287 by sywangyi was merged Jul 7, 2025 Loading…
[gaudi] Fix the CI test errors
#3286 by yuanwu2017 was merged Jul 7, 2025 Loading…
5 tasks
Optimum neuron 0.2.2
#3281 by dacorvo was merged Jul 3, 2025 Loading…
[gaudi] Gemma3 sliding window support
#3280 by sywangyi was merged Jul 1, 2025 Loading…
5 tasks
Neuron backend fix and patch version 3.3.4
#3273 by dacorvo was merged Jun 19, 2025 Loading…
doc: fix README
#3271 by dacorvo was merged Jun 18, 2025 Loading…
chore: prepare release 3.3.3
#3269 by dacorvo was merged Jun 18, 2025 Loading…
[Gaudi] use pad_token_id to pad input id
#3268 by sywangyi was merged Jun 17, 2025 Loading…
5 tasks
[Gaudi]Fix the integration-test issues
#3265 by yuanwu2017 was merged Jun 13, 2025 Loading…
5 tasks
[gaudi] HuggingFaceM4/idefics2-8b issue fix
#3264 by sywangyi was merged Jun 13, 2025 Loading…
[gaudi] Vlm rebase and issue fix in benchmark test
#3263 by sywangyi was merged Jun 12, 2025 Loading…
5 tasks
[Gaudi] Remove optimum-habana
#3261 by yuanwu2017 was merged Jun 12, 2025 Loading…
5 tasks
Bump neuron SDK version
#3260 by dacorvo was merged Jun 10, 2025 Loading…
Perf opt
#3256 by sywangyi was merged Jun 11, 2025 Loading…
Move the _update_cos_sin_cache into get_cos_sin
#3254 by yuanwu2017 was merged Jun 12, 2025 Loading…
5 tasks
Remove useless packages
#3253 by yuanwu2017 was merged Jun 3, 2025 Loading…
5 tasks
Prepare for 3.3.2
#3249 by danieldk was merged May 30, 2025 Loading…
5 tasks
Fix the Llama-4-Maverick-17B-128E crash issue
#3246 by yuanwu2017 was merged May 29, 2025 Loading…
5 tasks
[Gaudi] Fix the OOM issue of Llama-4-Scout-17B-16E-Instruct
#3245 by yuanwu2017 was merged May 29, 2025 Loading…
5 tasks
[Gaudi] Enable Qwen3_moe model
#3244 by yuanwu2017 was merged Jun 13, 2025 Loading…
5 tasks
fp8 compressed_tensors w8a8 support
#3242 by sywangyi was merged May 28, 2025 Loading…
5 tasks
Nix: switch to hf-nix
#3240 by danieldk was merged May 22, 2025 Loading…
5 tasks
ProTip! Adding no:label will show everything without a label.