e8e04fe8bc
Remove commented out info log actions from log configuration
2026-05-21 19:55:13 +00:00
6cb3acdd64
Add logging import and set logger level to WARNING
2026-05-21 19:50:21 +00:00
586ccbff1b
Update log action configuration to specify detailed error and info messages
2026-05-21 19:47:16 +00:00
bcc6b62277
Update log action configuration to enable error and info logging
2026-05-21 19:40:47 +00:00
3285d9118f
Enhance completions benchmark generator to extract words from a fallback Perl copyright file
2026-05-21 19:33:41 +00:00
f77d943d79
Refactor log message handling and improve word extraction in completions benchmark
2026-05-21 19:25:09 +00:00
976622a594
Remove nltk dep
2026-05-21 19:11:53 +00:00
3898a8a651
Update model server URL to remove port specification
2026-05-21 18:50:41 +00:00
170571714f
Add log message for model load event in Ollama configuration
2026-05-21 15:27:28 +00:00
81347ab8a0
Remove placeholder log messages for model load, error, and info
2026-05-21 15:11:30 +00:00
6bb0097829
Refactor model configuration and update log messages for Ollama
2026-05-21 15:11:25 +00:00
1cea6fbd2d
Update model server URL and port configuration
2026-05-20 13:34:45 +00:00
94926b74b6
Add log message for server listening status
2026-05-18 19:42:40 +00:00
d0347b0755
Update log file path and enhance load log messages
2026-05-18 18:41:14 +00:00
e02f4bc943
Lowered concurrency of vLLM and TGI benchmarks
2025-12-17 11:55:33 -08:00
bcb04b9a32
add missing comma
2025-12-17 11:40:40 -08:00
9daf171487
Increase queue limits for vLLM and TGI
2025-12-17 11:38:55 -08:00
29f836eb1a
Backwards compatible vLLM payload ( #75 )
...
* Support old vLLM payloads
2025-12-15 19:58:02 -08:00
4380d98c01
Use PyWorker SDK ( #67 )
...
* Change PyWorker to Worker SDK
* Moved /lib to vast-sdk (https://github.com/vast-ai/vast-sdk )
2025-12-15 19:33:03 -08:00
6b5b1341a7
update tgi client
2025-12-03 18:38:42 -08:00
8be92c03de
Merge pull request #69 from vast-ai/AUTO-874--fix-openai-worker-client
...
defaults to ENDPOINT_NAME and DEFAULT_MODEL but uses the flag first
2025-12-03 16:59:56 -08:00
adedb8ba90
defaults to ENDPOINT_NAME and DEFAULT_MODEL but uses the flag first if present
2025-12-03 16:57:28 -08:00
0bcd2219ea
Increase model wait time for vLLM
2025-12-03 12:38:52 -08:00
e0449cb3c7
add llama log
2025-11-21 10:22:16 -08:00
3adec1826d
minor changes
2025-11-11 17:11:38 -08:00
b55bfa9611
Updated clients, include vastai-sdk, handle non-UTF-8
2025-11-11 17:09:28 -08:00
bcecd6df40
Suppress matplot debug logs
2025-10-25 16:18:02 -07:00
0bf3247a34
fix completions and interactive client
2025-08-11 12:37:53 -07:00
8804e17201
download vast.ai's root certificate in order to make pyworker requests ( #25 )
2025-08-08 17:04:16 -07:00
e0be45f39a
Addresses breaking change in core pyworker ( #22 )
...
* Addresses breaking change in test_utils.py
Endpoint.get_endpoint_api_key() now requires instance
Moves the call to this function out of the APIClient and into main
* Ensure make_benchmark_payload has a value to calculate the workload
---------
Co-authored-by: Nader Arbabian <nader@vast.ai >
2025-07-18 16:11:10 -07:00
be2aafdb1f
fix pyright errors + revert to old way of handling cancelled api requests ( #23 )
2025-07-17 16:59:06 -07:00
69d9b7455f
OpenAI compatible worker ( #19 )
...
Adds initial support for OpenAI compatible inference servers
Available endpoints:
- `/v1/completions`
- `/v1/chat/completions`
2025-07-16 09:46:26 +01:00
Mikhail Yevchenko