text-generation-inference/server/text_generation_server/layers
Nicolas Patry 635dde8af9 Prefix caching (#2402)
* Prefix caching WIP

* Fixing prefix attention.

* Fixing flashinfer import.

* Fixing black.

* Fixing medusa (still wrong outputs, but functional).

* Just medusa values now.

* Fixing medusa without prefix caching.

* Fixing prefix caching.

* Medusa requires reshaping.

* Removing the logs.

* Remove router.nix

* Fixup:

- Remove logs
- Disable VLMs (they do not work)
- Disable prefix caching when user wants prefill logprobs.

* Update flake.lock

---------

Co-authored-by: Daniël de Kok <me@danieldk.eu>
2024-09-25 06:10:59 +00:00
..
attention Prefix caching (#2402) 2024-09-25 06:10:59 +00:00
awq feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
gptq fix: include create_exllama_buffers and set_device for exllama (#2407) 2024-09-25 06:06:17 +00:00
marlin Handle GPTQ-Marlin loading in GPTQMarlinWeightLoader (#2300) 2024-09-25 05:55:39 +00:00
__init__.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
bnb.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
conv.py Refactor layers. (#1866) 2024-07-17 05:36:58 +00:00
eetq.py feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248) 2024-09-25 05:30:41 +00:00
exl2.py Add support for Deepseek V2 (#2224) 2024-09-25 05:27:40 +00:00
fp8.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
layernorm.py Removing IPEX_AVAIL. (#2115) 2024-09-24 03:52:23 +00:00
linear.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
lora.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
medusa.py Prefix caching (#2402) 2024-09-25 06:10:59 +00:00
mlp.py MLPSpeculator. (#1865) 2024-07-17 05:36:58 +00:00
rotary.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
speculative.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00
tensor_parallel.py feat: add ruff and resolve issue (#2262) 2024-09-25 05:46:24 +00:00