ishaan-jaff
|
7891830136
|
(bump) 1.30.4
|
2024-03-08 21:20:02 -08:00 |
|
Ishaan Jaff
|
8036b48f14
|
Merge pull request #2408 from BerriAI/litellm_no_store_reqs
[FEAT-liteLLM Proxy] Incognito Requests - Don't log anything
|
2024-03-08 21:11:43 -08:00 |
|
Ishaan Jaff
|
9b94b0e591
|
Merge pull request #2411 from H0llyW00dzZ/docs
Update Docs for Kubernetes
|
2024-03-08 20:57:46 -08:00 |
|
H0llyW00dzZ
|
7004940ce4
|
Update Docs for Kubernetes
- [+] docs(deploy.md): add tip about using versioning or SHA digests instead of latest tag
|
2024-03-09 11:55:31 +07:00 |
|
ishaan-jaff
|
5850ff470f
|
(feat) disable/enable logging
|
2024-03-08 20:42:12 -08:00 |
|
Ishaan Jaff
|
54114c7e9d
|
Merge pull request #2409 from GuillermoBlasco/patch-2
Add quickstart deploy with k8s
|
2024-03-08 20:37:21 -08:00 |
|
Ishaan Jaff
|
0fc7b273e5
|
Merge pull request #2403 from BerriAI/litellm_api_version_client_side
[FEAT] AzureOpenAI - Pass `api_version` to litellm per request
|
2024-03-08 20:33:45 -08:00 |
|
Krrish Dholakia
|
0fb7afe820
|
feat(proxy_server.py): working /audio/transcription endpoint
|
2024-03-08 18:20:27 -08:00 |
|
Guillermo
|
bb427b4659
|
Update deploy.md
|
2024-03-09 02:30:17 +01:00 |
|
Guillermo
|
37b4dde7fd
|
Add quickstart deploy with k8s
|
2024-03-09 02:24:07 +01:00 |
|
ishaan-jaff
|
0a538fe679
|
(feat) use no-log to disable per request logging
|
2024-03-08 16:56:20 -08:00 |
|
ishaan-jaff
|
ddd231a8c2
|
(feat) use no-log as a litellm param
|
2024-03-08 16:46:38 -08:00 |
|
ishaan-jaff
|
d6dc28f0ed
|
(fix) proxy setting success callbacks
|
2024-03-08 16:27:53 -08:00 |
|
ishaan-jaff
|
4ff68c8562
|
(docs) no log requests
|
2024-03-08 16:26:25 -08:00 |
|
ishaan-jaff
|
986a526790
|
(feat) disable logging per request
|
2024-03-08 16:25:54 -08:00 |
|
Ishaan Jaff
|
ad4bfee3ee
|
Merge pull request #2406 from BerriAI/litellm_locust_load_test
[Feat] LiteLLM - use cpu_count for default num_workers, run locust load test
|
2024-03-08 15:41:40 -08:00 |
|
ishaan-jaff
|
9ed51e791b
|
(fix) default num workers
|
2024-03-08 15:24:08 -08:00 |
|
ishaan-jaff
|
2d71f54afb
|
(docs) load test litellm
|
2024-03-08 15:18:06 -08:00 |
|
Krrish Dholakia
|
cc0294b2f2
|
fix(proxy_server.py): fix tagging of endpoints
|
2024-03-08 14:29:31 -08:00 |
|
Krrish Dholakia
|
8c6d5b7f16
|
feat(proxy_server.py): supports /audio/transcription endpoint on proxy
|
2024-03-08 14:28:07 -08:00 |
|
Krrish Dholakia
|
fe125a5131
|
test(test_whisper.py): add testing for load balancing whisper endpoints on router
|
2024-03-08 14:19:37 -08:00 |
|
Krrish Dholakia
|
9274245a0b
|
test(test_whisper.py): fix getting path for audio file in test
|
2024-03-08 14:10:19 -08:00 |
|
Krrish Dholakia
|
6fa585d001
|
test(test_whisper.py): fix test
|
2024-03-08 14:02:34 -08:00 |
|
Krrish Dholakia
|
ae54b398d2
|
feat(router.py): add load balancing for async transcription calls
|
2024-03-08 13:58:15 -08:00 |
|
Krrish Dholakia
|
321769a74d
|
build(model_prices_and_context_window.json): add pricing for whisper endpoints (openai + azure)
|
2024-03-08 13:50:38 -08:00 |
|
Krrish Dholakia
|
6b1049217e
|
feat(azure.py): add support for calling whisper endpoints on azure
|
2024-03-08 13:48:38 -08:00 |
|
ishaan-jaff
|
65ccfc35ca
|
(fix) azure extra setting client
|
2024-03-08 13:44:39 -08:00 |
|
ishaan-jaff
|
2f6e15655a
|
(feat) set api_version for Azure
|
2024-03-08 13:38:29 -08:00 |
|
ishaan-jaff
|
d67c63b0c3
|
(fix) use azure api_version
|
2024-03-08 13:33:58 -08:00 |
|
ishaan-jaff
|
2aafbe390b
|
(feat) read passed api_version
|
2024-03-08 13:16:12 -08:00 |
|
Krish Dholakia
|
713f5991b8
|
Merge pull request #2402 from GuillermoBlasco/patch-1
docs: fix yaml typo in proxy/configs.md
|
2024-03-08 11:56:37 -08:00 |
|
Guillermo
|
a693045460
|
docs: fix yaml typo in proxy/configs.md
equals was used instead of : as key-value delimiter in yaml
|
2024-03-08 20:33:47 +01:00 |
|
Ishaan Jaff
|
85b981f602
|
Merge pull request #2399 from BerriAI/litellm_support_name_for_anthropic
[Feat] Support messages.name for claude-3, perplexity ai API
|
2024-03-08 10:47:45 -08:00 |
|
Krrish Dholakia
|
696eb54455
|
feat(main.py): support openai transcription endpoints
enable user to load balance between openai + azure transcription endpoints
|
2024-03-08 10:25:19 -08:00 |
|
ishaan-jaff
|
96e3696138
|
(fix) support name on perplexity/
|
2024-03-08 09:41:58 -08:00 |
|
ishaan-jaff
|
f70feb1806
|
(test) name with claude-3
|
2024-03-08 09:33:54 -08:00 |
|
Krrish Dholakia
|
f8f01e5224
|
bump: version 1.30.2 → 1.30.3
|
2024-03-08 08:12:36 -08:00 |
|
Krrish Dholakia
|
2f9a39f30c
|
refactor(main.py): trigger new build
|
2024-03-08 08:12:22 -08:00 |
|
Krrish Dholakia
|
0e7b30bec9
|
fix(utils.py): return function name for ollama_chat function calls
|
2024-03-08 08:01:10 -08:00 |
|
Krrish Dholakia
|
0cf056f493
|
fix(proxy_server.py): use argon2 for faster api key checking
0.04s latency boost on load test
|
2024-03-07 21:48:18 -08:00 |
|
ishaan-jaff
|
b4e12fb8fd
|
(docs) litellm cloud formation stack
|
2024-03-07 21:01:28 -08:00 |
|
ishaan-jaff
|
4a4d36d923
|
(feat) bump litellm
|
2024-03-07 20:45:34 -08:00 |
|
Ishaan Jaff
|
302473eef1
|
Merge pull request #2391 from BerriAI/litellm_cloudform_stack
(feat) LiteLLM AWS CloudFormation Stack Template
|
2024-03-07 20:44:46 -08:00 |
|
Ishaan Jaff
|
90d7b61ec2
|
Merge pull request #2393 from BerriAI/litellm_router_debug_get_dep
[Feat] Load Balancing - View Metrics about selected deployments in server logs
|
2024-03-07 20:44:18 -08:00 |
|
ishaan-jaff
|
86ac020b12
|
(fix) show latency per deployment on router debug logs
|
2024-03-07 18:50:45 -08:00 |
|
ishaan-jaff
|
6f0faca85b
|
(feat) print debug info per deployment
|
2024-03-07 18:33:09 -08:00 |
|
ishaan-jaff
|
323f15aa2f
|
(fix) litellm cloud formation stack
|
2024-03-07 18:06:59 -08:00 |
|
ishaan-jaff
|
2f960a9651
|
(feat) auto-scale
|
2024-03-07 17:51:12 -08:00 |
|
ishaan-jaff
|
702e46b53d
|
(build) stack with db
|
2024-03-07 17:50:14 -08:00 |
|
ishaan-jaff
|
da4b150398
|
(feat) init cloud form stack
|
2024-03-07 16:49:39 -08:00 |
|