Commit Graph

Select branches

Hide Pull Requests

JakeHillion/images-formatted

JakeHillion/poulwnyystws

JakeHillion/qolrqmoxuotr

JakeHillion/qotmmkpkktsv

JakeHillion/qqwursqotloo

JakeHillion/rwopytsxwtlp

JakeHillion/syyqxzsolzox

JakeHillion/torrents

JakeHillion/vmwnonkzsnuo

JakeHillion/vnwuyypxwqqs

JakeHillion/wnpzkupouslp

JakeHillion/yvqrzonuknxu

add-glm5-support

ai-slop

aiohttp

alexcheema/add-qwen3-coder-next

alexcheema/add-step-3.5-flash

alexcheema/continuous-batching

alexcheema/dashboard-stop-button

alexcheema/debug-state-catchup-race

alexcheema/event-index-liveness

alexcheema/external-model-paths

alexcheema/fix-download-resume-buttons

alexcheema/fix-instance-preparing-delay

alexcheema/fix-local-network-permission-reboot

alexcheema/fix-stuck-download-after-cancel

alexcheema/graceful-loading-shutdown

alexcheema/meta-instance

alexcheema/mlx-distributed-transfer

alexcheema/model-picker-downloaded-filter

alexcheema/model-selection-ux

alexcheema/mtp-speculative-decoding

alexcheema/no-silent-instance-override

alexcheema/rdma-health-detection

alexcheema/reproduce-gpu-lock

alexcheema/restore-thunderbolt-bridge-launchdaemon

alexcheema/robust-hf-config-parsing

alexcheema/runner-health-check

alexcheema/speculative-decoding

alexcheema/topology-download-indicators

alexcheema/trust-remote-code-cli-flag

architecture-based-tokenizer-checks

babbler

bootstrap-peer

bump-required-mem

ciaran/download-coordinator-crash

ciaran/eval

ciaran/handle-disconnects

ciaran/image-demo

ciaran/storage-management

consistent-placement-api

dashboard-show-failure-reasons

david/batched-kernels

david/lcb_eval

david/mla-context-parallel

david/new-kernels

david/new-kernels-v2

david/speculative-mtp

download-pause-delete

e2e-tests

failed=stopped

feat/bandwidth-aware-placement

feat/dashboard-light-mode

feat/dashboard-light-mode-v2

feat/e2e-chaos-tests

feat/mac-studio-rdma-port-warning

feat/meta-instance-dashboard

feat/meta-instance-dashboard-ui

feat/prefill-eta

fix-instance-preview-type

fix/1025

fix/instance-preview-type-mismatch

fix/no-downloads-model-loading

fix/rdma-tb5-tooltip

fix/tb5-detection

graduate-image-gen

handle-message-too-large

iroh

iroh-migration

jaccl-build-fix

leo/add-cuda-typings

leo/add-glm-5

leo/add-instance-settings

leo/add-logprobs-to-chatcompletion

leo/add-more-tensor-strategies

leo/add-tool-calling

leo/add-uneven-sharding

leo/address-rdma-gpu-locks

leo/dgx-spark-integrations

leo/exo-bench-conc-fix

leo/fix-small-pipeline-rdma

leo/fix-step35flash-parser

leo/gguf-maybe

leo/handle-low-memory-situations

leo/log-kimi-k25

leo/prefill-decode-really

leo/prepare-batch-implementation

leo/prioritise-thunderbolt-ip-for-ring

leo/profile-socket-connection-metrics

leo/reduce-log-spam

leo/send-from-last-rank

leo/test-branch

leo/test-model-hanging

leo/test-stuff-1

leo/tmp-test

leo/try-custom-mlx-branch

leo/use-sm121-branch

main

meta-instance-split/jaccl-sidechannel

new-bridge-script

nid-persist

optimize-dashboard

releases/v1.0.65

releases/v1.0.66

releases/v1.0.67

remove-custom-discovery

runner-opts

runner-refactor

runner-shutdown-vs-failed

rust-explore-2

sami/dashboard-tests

sami/flash

sami/iOS-app

sami/image-gen-safety

simplify-downloads

splitting-rust-rewrite-3

streaming-delete-hang

support-mlx-device-backends

test-app

vllm-nix

gh-screenshot-assets

pr-1465-screenshots

test-screenshots-tmp

v0.0.1-alpha

v0.0.10-alpha

v0.0.11-alpha

v0.0.12-alpha

v0.0.13-alpha

v0.0.15-alpha

v0.0.2-alpha

v0.0.3-alpha

v0.0.4-alpha

v0.0.5-alpha

v0.0.7-alpha

v0.0.8-alpha

v0.0.9-alpha

v1.0

v1.0.60-alpha.1

v1.0.60-alpha0

v1.0.61

v1.0.61-alpha.0

v1.0.61-alpha.1

v1.0.61-alpha.2

v1.0.62

v1.0.63

v1.0.64

v1.0.65

v1.0.66

v1.0.67

v1.0.68

v1.0.69

vv0.0.10-alpha

Mono Color

• 0eb5c0c624 mac runners Alex Cheema 2024-08-02 16:15:42 +01:00
• e10aa581ac cuda test Alex Cheema 2024-08-02 16:06:54 +01:00
• 23d2432cb9 test cuda Alex Cheema 2024-08-02 16:03:58 +01:00
• fcdf57b873 t Alex Cheema 2024-08-02 15:49:41 +01:00
• f9c427467e t Alex Cheema 2024-08-02 15:45:54 +01:00
• cf32ec9ab1 t Alex Cheema 2024-08-02 15:44:07 +01:00
• c5646ae00f t Alex Cheema 2024-08-02 15:42:59 +01:00
• 6b300112c8 t Alex Cheema 2024-08-02 15:41:51 +01:00
• 4095dea805 t Alex Cheema 2024-08-02 15:40:55 +01:00
• 9117125466 t Alex Cheema 2024-08-02 15:40:08 +01:00
• ec98b9cf65 t Alex Cheema 2024-08-02 15:38:36 +01:00
• fecd081047 t Alex Cheema 2024-08-02 15:36:15 +01:00
• 49664c46c0 t Alex Cheema 2024-08-02 15:35:25 +01:00
• 2564d7c2b4 docker runner Alex Cheema 2024-08-02 15:34:11 +01:00
• aa99c8ae50 trigger circleci Alex Cheema 2024-08-02 15:09:27 +01:00
• 3313151010 test cuda Alex Cheema 2024-08-02 14:58:19 +01:00
• 7599df7ffd trigger circleci Alex Cheema 2024-08-02 14:56:37 +01:00
• 0c3638f438 trigger circleci Alex Cheema 2024-08-02 14:54:15 +01:00
• a3b0650f30 use gpu.nvidia.medium Alex Cheema 2024-08-02 14:49:48 +01:00
• 3a0c9c8582 linux-cuda image Alex Cheema 2024-08-02 14:49:07 +01:00
• af2f98bad4 run tinygrad tests on gpu.nvidia.small.gen2 (NVIDIA A10G 24GB) Alex Cheema 2024-08-02 14:47:25 +01:00
• 0fd6bd91a0 run tinygrad with llama-3-8b Alex Cheema 2024-08-02 14:20:24 +01:00
• eafed8e16e fix legacy model loading Alex Cheema 2024-08-02 14:18:31 +01:00
• 08e8cacf01 run integration test for each inference engine Alex Cheema 2024-08-02 13:47:06 +01:00
• 32bb44b3a2 request to both nodes in integration test, dont preload the model - exo should be robust against that Alex Cheema 2024-08-02 11:51:53 +01:00
• c06124c637 fix circleci badge Alex Cheema 2024-08-02 11:48:52 +01:00
• 0b06516af8 Merge pull request #115 from exo-explore/circleci-project-setup Alex CheemaandGitHub 2024-08-02 11:45:52 +01:00
• f4b0f1ca02 replace tests badge with circleci Alex Cheema 2024-08-02 11:45:09 +01:00
• e3a524fd89 Merge pull request #114 from exo-explore/circleci-project-setup Alex CheemaandGitHub 2024-08-02 11:41:53 +01:00
• 96969e3540 prefix matching logic Alex Cheema 2024-08-02 11:28:48 +01:00
• 7c0923279c trigger circleci Alex Cheema 2024-08-02 11:25:34 +01:00
• 2a8f1ae4c5 get rid of caches. circeci downloads fast enough Alex Cheema 2024-08-02 11:13:53 +01:00
• 54ea5dbb5c only remove the matching prefix from the prompt if its length is less than the prompt Alex Cheema 2024-08-02 11:11:16 +01:00
• 67ad3f57a1 use llama 3.1 in tests Alex Cheema 2024-08-02 10:56:29 +01:00
• 92b66e275f fix cache Alex Cheema 2024-08-02 10:50:45 +01:00
• cf3dae9570 circleci: separate hf, tinygrad caches Alex Cheema 2024-08-02 10:45:53 +01:00
• faadfa29dd circleci chatgpt integration test Alex Cheema 2024-08-02 10:44:35 +01:00
• 9a03991f1a cache key Alex Cheema 2024-08-02 10:39:46 +01:00
• 2065c7751a orb Alex Cheema 2024-08-02 10:27:12 +01:00
• cf4cddccc1 port github workflow to circleci Alex Cheema 2024-08-02 10:25:30 +01:00
• 21b0bf8777 Update config.yml Alex CheemaandGitHub 2024-08-02 10:11:00 +01:00
• 997fcaff35 CircleCI Commit Alex Cheema 2024-08-02 10:09:16 +01:00
• f5755ea198 give explicit node ids when running on the same instance in tests, otherewise they use the same one because of sticky node ids Alex Cheema 2024-08-01 01:24:50 +01:00
• 4faa6c06f4 add support for selective model downloading. related: #16 Alex Cheema 2024-08-01 01:22:41 +01:00
• be3a09c28b rm logs Alex Cheema 2024-07-31 23:24:30 +01:00
• 0bfb8e3b6d sticky node ids #16 Alex Cheema 2024-07-31 23:20:15 +01:00
• 980d5d2c5b bring back TINYGRAD_DEBUG. not sure why it was removed Alex Cheema 2024-07-31 22:56:53 +01:00
• 76766253cd fix regression introduced by image_str for tinygrad Alex Cheema 2024-07-31 22:53:46 +01:00
• 1d54f10514 pass on tinygrad set_on_download_progress Alex Cheema 2024-07-31 22:50:04 +01:00
• d6a7e46324 async model downloading with download progress. fixes #102. related: #16 #104 Alex Cheema 2024-07-31 22:47:03 +01:00
• 5c67e24c35 smart prompt longest prefix matching to avoid sending the same text through the NN again. speeds up prefill significantly Alex Cheema 2024-07-31 14:27:10 +01:00
• 94ac9463a7 fix model id for llama 3.1 405b now its finally on the hub Alex Cheema 2024-07-31 10:16:30 +01:00
• 178fb75c84 fix image api prompt encoding Alex Cheema 2024-07-30 23:56:30 +01:00
• 2d20000964 use AutoProcessor with use_fast=False since there's a bug with use_fast=True where whitespace is removed on single token decodes Alex Cheema 2024-07-30 22:40:02 +01:00
• 0ec77e1a99 Merge pull request #88 from varshith15/main Alex CheemaandGitHub 2024-07-30 20:02:47 +01:00
• af1c7ce327 add support for image upload to tinychat for vision models Alex Cheema 2024-07-30 20:01:35 +01:00
• 0d45a855fb increase max request size to send raw images, make image download from url async, use chatgpt-compatible convention for images Alex Cheema 2024-07-30 20:01:18 +01:00
• e68d06f4ef move model-selector styles to index.css Alex Cheema 2024-07-30 14:51:22 +01:00
• 78db451d7e add pillow to main dependencies Alex Cheema 2024-07-30 14:27:45 +01:00
• 824f05263f Merge branch 'main' into HEAD Alex Cheema 2024-07-30 14:18:10 +01:00
• 142682645f bump up tinygrad version Alex Cheema 2024-07-30 10:02:20 +01:00
• 8d3d3df1dd update readme Varshith 2024-07-28 16:14:27 +05:30
• acc94b50c7 chatgpt api integration Varshith 2024-07-28 16:12:21 +05:30
• 33cbacf513 fix llava sanitize Alex Cheema 2024-07-27 21:31:36 -07:00
• 2fb961fccd stick to same convention as new llama Alex Cheema 2024-07-27 21:04:13 -07:00
• b44b917151 add pillow as testing dependency Alex Cheema 2024-07-27 20:23:03 -07:00
• 2aa1e24ea9 remove unused torch import Alex Cheema 2024-07-27 20:22:56 -07:00
• 833e7f3396 rename sharded_llava -> llava to match new convention Alex Cheema 2024-07-27 20:19:55 -07:00
• 7d5eed1111 Merge branch 'main' into HEAD Alex Cheema 2024-07-27 20:17:12 -07:00
• 044d189ccc Merge pull request #94 from mzbac/mlx_refactor Alex CheemaandGitHub 2024-07-27 20:02:51 -07:00
• 909d5ef8ba Merge branch 'main' into mlx_refactor Alex Cheema 2024-07-27 20:01:56 -07:00
• 63e51a8270 formatting Alex Cheema 2024-07-27 20:00:39 -07:00
• 6695b019a2 format format.py Alex Cheema 2024-07-27 19:57:18 -07:00
• 1dc08fecaa increase max line length to 200 Alex Cheema 2024-07-27 19:56:50 -07:00
• 444137776a formatting Alex Cheema 2024-07-27 19:55:27 -07:00
• a6bb8ddf41 update deepseek sanitize to shard layers first before handle switch Anchen 2024-07-28 12:58:09 +10:00
• cb217b7b77 format format.py Alex Cheema 2024-07-27 19:57:18 -07:00
• 4cb36a7f55 increase max line length to 200 Alex Cheema 2024-07-27 19:56:50 -07:00
• d94e3f9ce4 formatting Alex Cheema 2024-07-27 19:55:27 -07:00
• 666b1c83ee refactor(mlx): model sharding and add deepseek v2 support Anchen 2024-07-28 12:46:38 +10:00
• 931ced7c01 fix a few more linter errors Alex Cheema 2024-07-27 17:09:34 -07:00
• 57b2f2a4e2 fix ruff lint errors Alex Cheema 2024-07-27 17:08:32 -07:00
• ce761038ac formatting / linting Alex Cheema 2024-07-27 17:01:37 -07:00
• f1bd5fe152 Merge pull request #90 from xeb/main Alex CheemaandGitHub 2024-07-27 16:06:33 -07:00
• f051ebe6e0 remove accidentally added files Alex Cheema 2024-07-27 16:05:09 -07:00
• 5eafd5a305 try/except for decode, #75 Mark Kockerbeck 2024-07-27 13:00:14 -07:00
• 2849128d6a processor load Varshith 2024-07-28 01:03:34 +05:30
• 6ed76b3493 Merge branch 'main' into main Varshith BathiniandGitHub 2024-07-28 01:00:08 +05:30
• 54993995dc conflicts Varshith 2024-07-28 00:44:41 +05:30
• 9d2616b9cf shareded inference Varshith 2024-07-28 00:30:34 +05:30
• faa1319470 disable chatgpt api integration test, github changed something in their mac runners? perhaps time to switch over to circleci like mlx Alex Cheema 2024-07-26 23:52:22 -07:00
• 67a1aaa823 check processes in github workflow Alex Cheema 2024-07-26 23:37:11 -07:00
• 9a3ac273a9 Merge pull request #77 from Cloud1590/main Alex CheemaandGitHub 2024-07-26 22:52:15 -07:00
• 628d8679b0 force mlx inference engine in github workflow, where it defaults to tinygrad because it's running on 'model': 'Apple Virtual Machine 1', 'chip': 'Apple M1 (Virtual)' Alex Cheema 2024-07-26 21:46:41 -07:00
• e856d7f7f9 log chatgpt integration test output from each process on github workflow failure Alex Cheema 2024-07-26 21:37:42 -07:00
• d2fa7b247e Showing the message only if successfully decoded, #75 Mark Kockerbeck 2024-07-26 12:06:17 -07:00
• f1cd5ae7a6 Merge branch 'main' of github.com:xeb/exo Mark Kockerbeck 2024-07-26 12:04:18 -07:00
• 4f5ab78d9d Addressing issue #75 to avoid decoding binary packets Mark Kockerbeck 2024-07-26 12:03:49 -07:00
• 7cbf6a35bd working test Varshith 2024-07-26 19:12:42 +05:30
• 5a23376059 add log_request middleware if DEBUG>=2 to chatgpt api to debug api issues, default always to llama-3.1-8b Alex Cheema 2024-07-25 20:33:26 -07:00