huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-21 23:12:07 +00:00
Code Issues Packages Projects Releases Wiki Activity
bdc47394d2
text-generation-inference/server/text_generation_server/models/custom_modeling
History
drbh bdc47394d2 feat: support phi3.5 moe (#2479) 
* feat: support phi3.5 moe model loading

* fix: prefer llama base model and improve rotary logic

* feat: return reasonable generation and add integration test

* fix: run lint and update docs

* fix: rerun lint for openapi docs

* fix: prefer do_sample false unless temp is set by user, and update chat tests

* fix: small typo adjustments

* fix: consolidate long rope paths

* fix: revert greedy by default and test changes

* Vendor configuration so that we don't have to `trust_remote_code`

* Use SparseMoELayer

* Add support for dense MoE

* Some type annotations

* Add the usual model tests

* Ruff.

---------

Co-authored-by: Daniël de Kok <me@danieldk.eu>
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-10-25 09:12:03 +00:00
..
__init__.py feat(server): flash santacoder (#153) 2023-04-03 19:06:42 +02:00
bloom_modeling.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
clip.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
flash_cohere_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_dbrx_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_deepseek_v2_modeling.py Update ROCM libs and improvements (#2579) 2024-10-25 09:01:04 +00:00
flash_gemma2_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_gemma_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_gpt2_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_gptj_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_llama_modeling.py feat: support phi3.5 moe (#2479) 2024-10-25 09:12:03 +00:00
flash_mistral_modeling.py Update ROCM libs and improvements (#2579) 2024-10-25 09:01:04 +00:00
flash_mixtral_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_neox_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_pali_gemma_modeling.py Lots of improvements (Still 2 allocators) (#2449) 2024-09-25 06:13:11 +00:00
flash_phi_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_phi_moe_modeling.py feat: support phi3.5 moe (#2479) 2024-10-25 09:12:03 +00:00
flash_qwen2_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_rw_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_santacoder_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
flash_starcoder2_modeling.py Improve support for GPUs with capability < 8 (#2575) 2024-10-25 09:01:04 +00:00
idefics2.py Lots of improvements (Still 2 allocators) (#2449) 2024-09-25 06:13:11 +00:00
idefics_config.py chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
idefics_image_processing.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
idefics_modeling.py enable HuggingFaceM4/idefics-9b in intel gpu (#2338) 2024-09-25 05:55:39 +00:00
idefics_perceiver.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
idefics_processing.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
idefics_vision.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
llava_next.py Make Gaudi adapt to the tgi 2.3.0 2024-09-26 06:04:55 +00:00
mamba_modeling.py Refactor layers. (#1866) 2024-07-17 05:36:58 +00:00
mpt_modeling.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
neox_modeling.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
opt_modeling.py Fix the prefix for OPT model in opt_modelling.py #2370 (CI RUN) (#2371) 2024-09-25 05:55:39 +00:00
phi_modeling.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
siglip.py Fix: don't apply post layernorm in SiglipVisionTransformer (#2459) 2024-09-25 06:10:59 +00:00
t5_modeling.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
vlm.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00