| .. |
|
rpc
|
b5aa11020b
api: fix crashes under very high loads (#878)
|
hace 4 semanas |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
hace 1 año |
|
api_server.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
hace 3 semanas |
|
args.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hace 4 meses |
|
logits_processors.py
|
62111fab17
feat: allow serving encoder-decoder models in the API server (#664)
|
hace 4 meses |
|
protocol.py
|
3392b81bf9
sampler: allow parsing sampler order using strings (#858)
|
hace 1 mes |
|
run_batch.py
|
81fa31bcaf
feat: embeddings support for batched OAI endpoint (#676)
|
hace 4 meses |
|
samplers.json
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
hace 10 meses |
|
serving_chat.py
|
61c7182491
feat: enable prompt logprobs in OpenAI API (#720)
|
hace 4 meses |
|
serving_completions.py
|
61c7182491
feat: enable prompt logprobs in OpenAI API (#720)
|
hace 4 meses |
|
serving_embedding.py
|
ebf01d665b
fix: disable embeddings API for chat models (#710)
|
hace 4 meses |
|
serving_engine.py
|
1d3a1fec47
feat: add load/unload endpoints for soft-prompts (#694)
|
hace 4 meses |
|
serving_tokenization.py
|
3648170750
fix: gracefully handle missing chat template (#642)
|
hace 4 meses |
AlpinDale
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)