Commit graph

8725 commits

Author SHA1 Message Date
ishaan-jaff
01aa7b3e6e (fix) deploy litellm-helm 2024-03-16 10:10:47 -07:00
ishaan-jaff
54dceea4b0 (fix) releasing litellm helm as "litellm-helm" 2024-03-16 10:06:14 -07:00
ishaan-jaff
919fe14257 (fix) release helm chart as litellm-helm 2024-03-16 10:03:29 -07:00
Krish Dholakia
c1495c0d1c
Merge pull request #2527 from lazyhope/support_anthropic_function_result
Add function call result submission support for Claude 3 models
2024-03-16 09:58:33 -07:00
Krish Dholakia
0368a335e6
Merge branch 'main' into support_anthropic_function_result 2024-03-16 09:58:08 -07:00
ishaan-jaff
5a87ac8047 (feat) publish litellm helm charts 2024-03-16 09:53:41 -07:00
ishaan-jaff
177571bea3 (fix) backoff import 2024-03-16 08:53:06 -07:00
Krrish Dholakia
2d2731c3b5 docs(caching.md): add batch redis requests to docs 2024-03-15 23:01:08 -07:00
Krish Dholakia
f3cf1ec71f
Update proxy_server_config.yaml 2024-03-15 22:40:39 -07:00
Krish Dholakia
24e673dd6d
Update proxy_server_config.yaml 2024-03-15 22:19:37 -07:00
ishaan-jaff
2d7ca36ec4 (fix) errant print saying "Error importing .." msg 2024-03-15 21:47:52 -07:00
Krish Dholakia
88152c77c5
Update Dockerfile 2024-03-15 21:47:13 -07:00
Krish Dholakia
961c3548f5
Update proxy_server_config.yaml 2024-03-15 19:06:06 -07:00
Krrish Dholakia
a12e55932e bump: version 1.31.15 → 1.31.16 2024-03-15 19:03:15 -07:00
Krish Dholakia
4969ae0e9d
Merge pull request #2542 from BerriAI/litellm_redis_perf_improvements
89% Caching improvement - Async Redis completion calls + batch redis GET requests for a given key + call type
2024-03-15 18:58:36 -07:00
Krrish Dholakia
909341c4f2 fix(utils.py): async add to cache - for streaming 2024-03-15 18:25:40 -07:00
Krrish Dholakia
4912ad5cf4 test(test_custom_logger.py): fix async streaming test 2024-03-15 18:18:54 -07:00
Krrish Dholakia
3072137739 test(test_caching.py): fix async tests 2024-03-15 18:09:25 -07:00
ishaan-jaff
92b198f6c5 (docs) litellm + helm chart 2024-03-15 17:04:51 -07:00
Ishaan Jaff
8cfa0b64ce
Merge pull request #2541 from udit-001/docs/chatlitellm-langfuse
docs(langfuse): add chatlitellm section
2024-03-15 16:32:01 -07:00
Ishaan Jaff
5169fe9836
Merge pull request #2544 from BerriAI/litellm_helm_chart_fixes
[Docs+Fixes] Litellm helm chart use k8 1.21
2024-03-15 16:30:38 -07:00
ishaan-jaff
d24eb263f2 (ci/cd) dispatch to run load test 2024-03-15 16:27:47 -07:00
ishaan-jaff
a2a6c474e0 (ci/cd) dispatch to run load test 2024-03-15 16:27:34 -07:00
ishaan-jaff
974d654189 (fix) clean up litellm helm chart 2024-03-15 16:20:41 -07:00
ishaan-jaff
3108c91ebd (docs) using litellm + helm charts 2024-03-15 16:20:26 -07:00
ishaan-jaff
fb4fa5af72 (docs) using litellm helm 2024-03-15 16:09:27 -07:00
ishaan-jaff
4a33c53619 (fix) docs litellm helm chart 2024-03-15 16:07:43 -07:00
Ishaan Jaff
eb071d8101
Merge pull request #2540 from BerriAI/litellm_fix_error_message_on_bad_key
(fix) Proxy - fix error message raised on passing invalid tokens
2024-03-15 15:49:39 -07:00
ishaan-jaff
21202a397f (ci/cd) final working load test / benchmark 2024-03-15 15:46:59 -07:00
ishaan-jaff
0552679a58 (ci/cd) load test 2024-03-15 15:30:53 -07:00
ishaan-jaff
06e319fceb (ci/cd) run load test 2024-03-15 15:25:33 -07:00
ishaan-jaff
a98c5fdbeb (ci/cd) load test 2024-03-15 15:14:26 -07:00
Udit
4a232f4ab3 docs(langfuse): update langfuse casing 2024-03-16 03:34:47 +05:30
Udit
b8dbcd7ac3 docs(langfuse): update section titles 2024-03-16 03:33:14 +05:30
Udit
31fb2d0219 docs(langfuse): fix missing litellm import 2024-03-16 03:30:01 +05:30
Udit
1220eb3c7a docs(langfuse): update chatlitellm section 2024-03-16 03:28:19 +05:30
ishaan-jaff
4153b74157 (fix) run load test on new releases, workflow dispatches 2024-03-15 14:56:49 -07:00
ishaan-jaff
82b8fbabcb (fix) run prod load tests for 5 mins 2024-03-15 14:55:26 -07:00
Krrish Dholakia
8a20ea795b feat(batch_redis_get.py): batch redis GET requests for a given key + call type
reduces number of redis requests. 85ms latency improvement over 3 minutes of load (19k requests).
2024-03-15 14:54:16 -07:00
Udit
acd56b174c docs(langfuse): add chatlitellm section 2024-03-16 03:24:07 +05:30
ishaan-jaff
fd93a68b0d (fix) fix error message raised on passing invalid tokens 2024-03-15 14:50:34 -07:00
Krrish Dholakia
226953e1d8 feat(batch_redis_get.py): batch redis GET requests for a given key + call type
reduces the number of GET requests we're making in high-throughput scenarios
2024-03-15 14:40:11 -07:00
ishaan-jaff
a5b8fb0ee7 (ci/cd) load test should allow only 5% fails 2024-03-15 13:11:15 -07:00
ishaan-jaff
6ee6fb6c73 (ci/cd) use deployed github release for load testing 2024-03-15 12:55:33 -07:00
ishaan-jaff
f3209b63cd (fix) locustfile used in load test 2024-03-15 12:38:37 -07:00
ishaan-jaff
310811681a (ci/cd) run load test 2024-03-15 12:29:13 -07:00
ishaan-jaff
62c5852c52 (ci/cd) view load test results 2024-03-15 12:25:32 -07:00
ishaan-jaff
493d24e4f7 (ci/cd) view load test results 2024-03-15 12:19:36 -07:00
ishaan-jaff
fe9878017f (ci/cd) show load test results 2024-03-15 12:17:16 -07:00
ishaan-jaff
c89dba7949 (ci/cd) visualize load test results 2024-03-15 11:59:17 -07:00