preemo_text-generation-infe.../server/text_generation_server/models
Michael Feil ff703cb867
Adding ctranslate2 quantization and inference: moving the contribution (#1)
* rebaseing the commit on preemo fork.

* reformatting and changes.

* update dockerfile

* update changes for dockerfile

* adapt path

* rebaseing the commit on preemo fork.

* reformatting and changes.

* update dockerfile

* update changes for dockerfile

* adapt path

---------

Co-authored-by: michaelfeil <me@michaelfeil.eu>
2023-10-02 11:12:49 -07:00
..
custom_modeling Don't enable custom kernels if CUDA is not available (#6) 2023-08-02 09:51:54 -07:00
__init__.py Adding ctranslate2 quantization and inference: moving the contribution (#1) 2023-10-02 11:12:49 -07:00
bloom.py Add AutoCausalLM (#5) 2023-08-02 09:35:40 -07:00
causal_lm.py Add AutoCausalLM (#5) 2023-08-02 09:35:40 -07:00
ct2_causal_lm.py Adding ctranslate2 quantization and inference: moving the contribution (#1) 2023-10-02 11:12:49 -07:00
flash_causal_lm.py Initialize v_cache to avoid NaNs (#12) 2023-08-23 14:23:59 -07:00
flash_llama.py feat(server): Using `quantize_config.json` instead of GPTQ_BITS env variables. (#671) 2023-07-25 13:00:27 +02:00
flash_neox.py feat(server): Using `quantize_config.json` instead of GPTQ_BITS env variables. (#671) 2023-07-25 13:00:27 +02:00
flash_rw.py fix(server): fix quantization python requirements (#708) 2023-07-27 12:28:10 +02:00
flash_santacoder.py feat(server): Using `quantize_config.json` instead of GPTQ_BITS env variables. (#671) 2023-07-25 13:00:27 +02:00
galactica.py Add AutoCausalLM (#5) 2023-08-02 09:35:40 -07:00
gpt_neox.py Add AutoCausalLM (#5) 2023-08-02 09:35:40 -07:00
model.py feat: add cuda memory fraction (#659) 2023-07-24 11:43:58 +02:00
mpt.py Add AutoCausalLM (#5) 2023-08-02 09:35:40 -07:00
opt.py Add AutoCausalLM (#5) 2023-08-02 09:35:40 -07:00
rw.py Add AutoCausalLM (#5) 2023-08-02 09:35:40 -07:00
santacoder.py Add AutoCausalLM (#5) 2023-08-02 09:35:40 -07:00
seq2seq_lm.py feat: Add the option to force another dtype than `f16`. (#513) 2023-06-30 20:30:09 +02:00
t5.py fix(server): T5 weights names. (#582) 2023-07-12 10:01:42 +02:00
types.py feat(server): support vectorized warpers in flash causal lm (#317) 2023-05-26 12:30:27 +02:00