Commit Graph

53 Commits

Author SHA1 Message Date
Aaron Pham
ad9107958d feat: continuous batching with vLLM (#349)
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* feat: continuous batching

Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com>

* chore: add changeloe

Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com>

* chore: add one shot generation

Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-09-14 03:09:36 -04:00
Aaron Pham
35e6945e86 fix(serialisation): vLLM safetensors support (#324)
* fix(serilisation): vllm support for safetensors

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>

* chore: running tools

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: generalize one shot generation

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: add changelog [skip ci]

Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com>
2023-09-12 17:44:01 -04:00
Alan Poulain
88d7ba7ca8 fix(vllm): Make sure to use max number of GPUs available (#326)
* fix(serving): vllm bad num_gpus

Signed-off-by: Alan Poulain <contact@alanpoulain.eu>

* ci: auto fixes from pre-commit.ci

For more information, see https://pre-commit.ci

---------

Signed-off-by: Alan Poulain <contact@alanpoulain.eu>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2023-09-12 12:45:00 -04:00
Aaron Pham
fddd0bf95e feat: bootstrap documentation site (#252)
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: GutZuFusss <leon.ikinger@googlemail.com>
Co-authored-by: GutZuFusss <leon.ikinger@googlemail.com>
2023-09-12 12:28:29 -04:00
aarnphm-ec2-dev
8530a067ea chore(serialisation): dump quantization_config.json to conform with
optimum load

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-09-07 16:50:50 +00:00
Aaron
0d50aa00b9 chore: add openllm-core as meta dependencies
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-09-07 10:31:40 -04:00
Aaron Pham
7e2c8428bb infra: prepare for release 0.3.3 [generated] [skip ci]
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
2023-09-07 01:51:18 +00:00
aarnphm-ec2-dev
8173cb09a5 fix(quantize): dyn quant for int8 and int4
only set tokenizer when it is gptq

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-09-07 01:48:45 +00:00
Aaron Pham
fd18c8be01 infra: prepare for release 0.3.2 [generated] [skip ci]
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
2023-09-06 19:03:40 +00:00
Aaron
675b372981 fix: synchronize device for inference
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-09-06 14:08:52 -04:00
Aaron Pham
b61005424b infra: prepare for release 0.3.1 [generated] [skip ci]
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
2023-09-06 17:49:58 +00:00
Aaron
887ffa9aa0 chore: cleanup pre-commit jobs and update usage
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-09-05 10:06:36 -04:00
aarnphm-ec2-dev
f43c721579 chore: only add bentomodel branch during generated service with
OpenLLM

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-09-05 01:08:23 +00:00
Aaron Pham
06a68ade7d infra: prepare for release 0.3.0 [generated] [skip ci]
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
2023-09-04 19:03:41 +00:00
Aaron
5eea40a599 chore(readme): update README for release [generated] [skip ci]
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-09-04 15:02:01 -04:00
Aaron Pham
956b3a53bc fix(gptq): use upstream integration (#297)
* wip

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>

* feat: GPTQ transformers integration

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>

* fix: only load if variable is available and add changelog

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>

* chore: remove boilerplate check

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-09-04 14:05:50 -04:00
aarnphm-ec2-dev
7d893e6cd2 chore: ignore new lines split [skip ci]
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-09-01 17:00:49 +00:00
Aaron Pham
608de0b667 fix(serving): vllm distributed size (#285)
* chore(weights): ignore gguf pattern for non GGML backend

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>

* chore: correct fix num_gpus to be divisble by 2

This depends on the attention_heads from given models

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-09-01 12:37:10 -04:00
Aaron Pham
b7af7765d4 fix(yapf): align weird new lines break [generated] [skip ci] (#284)
fix(yapf): align weird new lines break

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-09-01 05:34:22 -04:00
Aaron Pham
3e45530abd refactor(breaking): unify LLM API (#283)
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-09-01 05:15:19 -04:00
Aaron
b545ad2ad1 style: google
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-08-30 13:52:35 -04:00
Aaron Pham
c9cef1d773 fix: persistent styling between ruff and yapf (#279) 2023-08-30 11:37:41 -04:00
Aaron Pham
2036d4e015 chore(build): use latest vllm pre-built kernel (#261) 2023-08-26 09:02:52 -04:00
aarnphm-ec2-dev
806a663e4a chore(style): add one blank line
to conform with Google style

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-08-26 11:36:57 +00:00
Aaron Pham
938fd362bb feat(vllm): streaming (#260) 2023-08-26 07:27:32 -04:00
Aaron Pham
46c8904806 cron(style): run formatter [generated] [skip ci] (#257) 2023-08-25 06:38:59 -04:00
Aaron Pham
816bfdcc19 infra: prepare for release 0.2.27 [generated] [skip ci]
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
2023-08-25 09:28:49 +00:00
aarnphm-ec2-dev
dae38cdba1 chore: update external dependencies [skip ci]
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-08-25 09:27:26 +00:00
Aaron Pham
08dc6ed2ba chore: ignore peft and fix adapter loading issue (#255)
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2023-08-25 04:36:35 -04:00
Aaron
787ce1b3b6 chore(style): synchronized style across packages [skip ci]
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-08-23 08:46:22 -04:00
Aaron Pham
bbd9aa7646 refactor(contrib): similar namespace [clojure-ui build] (#251) 2023-08-23 00:21:59 -04:00
aarnphm-ec2-dev
eddbc06374 chore(style): reduce line length and truncate compression
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-08-22 17:02:00 +00:00
aarnphm-ec2-dev
1488fbb167 chore(style): enable yapf to match with style guidelines
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-08-22 14:03:06 +00:00
Aaron Pham
3ffb25a872 refactor: packages (#249) 2023-08-22 08:55:46 -04:00
aarnphm-ec2-dev
9e371d2ead fix(generate): Correct set batch output for generate from iterator
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-08-21 12:02:35 +00:00
Aaron Pham
9e205b4963 feat: token streaming and SSE support (#240) 2023-08-20 07:32:49 -04:00
Aaron Pham
ec3852b5b8 infra: prepare for release 0.2.26 [generated] [skip ci]
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
2023-08-17 19:53:56 +00:00
Aaron Pham
4140d160b8 feat(embedding): Adding generic endpoint (#227) 2023-08-17 15:17:00 -04:00
aarnphm-ec2-dev
d5c4066ff4 fix(generation): unecessary casting [ec2 build] [wheel build]
This breaks when compiled to cfunc

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-08-17 16:34:59 +00:00
Aaron Pham
3ca1fde9ff fix(binary): correct folders when building standalone installer (#228) 2023-08-17 09:56:08 -04:00
Aaron Pham
017e57653b infra: prepare for release 0.2.25 [generated] [skip ci]
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
2023-08-16 11:42:47 +00:00
aarnphm-ec2-dev
3363ee158b fix(container): set correct PyTorch version not to override cuda
wheels

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-08-16 10:46:49 +00:00
Aaron Pham
8796d0d63d feat(models): add vLLM support for Falcon (#223) 2023-08-16 05:57:42 -04:00
Aaron Pham
3a73aacb01 chore(ci): add dependabot and fix vllm release container (#217) 2023-08-16 05:43:41 -04:00
Aaron Pham
ccca49af04 fix(ci): remove broken build hooks (#216) 2023-08-16 04:49:12 -04:00
Aaron
af8cb73832 fix: latest vllm build
sync changelog with monorepo for sdist installation

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-08-16 04:03:34 -04:00
GutZuFusss
4cad367ab5 feat(contrib): ClojureScript UI (#89)
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
2023-08-16 03:30:44 -04:00
Aaron
6b0ab17018 chore: remove unnecessary headers
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-08-15 18:15:54 -04:00
Aaron
78ae2b3843 fix(metadata): hooks for metadata pypi [skip ci]
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-08-15 06:15:51 -04:00
Aaron
21ce11aaa8 chore: add symlink for changelog [skip ci]
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
2023-08-15 05:27:14 -04:00