AlpinDale
|
688d56993a
add logit scale for command-r
|
10 months ago |
AlpinDale
|
f1ea36a445
add some imports
|
10 months ago |
AlpinDale
|
06d88bb8fd
logitproc for cohere
|
10 months ago |
AlpinDale
|
582e9efc12
support command-r+ model
|
10 months ago |
AlpinDale
|
2410957e87
simplify sampler in llama
|
10 months ago |
AlpinDale
|
15308ffb5b
compute logits in model_runner
|
10 months ago |
AlpinDale
|
860250150b
pipe in logitproc in lora
|
10 months ago |
AlpinDale
|
b01eec7c35
stop workflows on dev
|
10 months ago |
AlpinDale
|
f01c668259
clean up sampler
|
10 months ago |
AlpinDale
|
fa6af97a5a
add new logits processor
|
10 months ago |
AlpinDale
|
78d66f16d1
Chunked Prefill Part 1 (#384)
|
10 months ago |
AlpinDale
|
9181fa0396
feat: Triton kernels for sampling (#383)
|
10 months ago |
AlpinDale
|
e3252edd07
fix: remove event and stream, add typing (#382)
|
10 months ago |
AlpinDale
|
375f24ccca
fix: optimize context shift performance (#380)
|
10 months ago |
AlpinDale
|
33b3786175
fix: cache neuron checks (#379)
|
10 months ago |
AlpinDale
|
8c9cabf4c8
fix: display error in ray before deadlock (#378)
|
10 months ago |
AlpinDale
|
f587953f46
fix: yapf
|
10 months ago |
AlpinDale
|
4b99ac15b7
fix: do not deepcopy metadata
|
10 months ago |
AlpinDale
|
17b034613d
chore: make metadata a dataclass (#377)
|
10 months ago |
AlpinDale
|
9534fcfb7b
fix: build error
|
10 months ago |
AlpinDale
|
0b35176089
feat: add context-free grammars (#376)
|
10 months ago |
AlpinDale
|
feb5840f2a
feat: async tokenization (#374)
|
10 months ago |
IggoOnCode
|
2aec297c55
feat: add embeddings endpoint to openai rest-api server. (#363)
|
10 months ago |
AlpinDale
|
29c241c115
fix: explicitly disallow installation on non-linux platforms (#373)
|
10 months ago |
AlpinDale
|
439a826712
fix: broadcast group
|
10 months ago |
AlpinDale
|
935027bdcc
feat: dynamic shared memory allocation for moe align block size (#372)
|
10 months ago |
AlpinDale
|
97a2b26c97
fix: assertion error when use_sliding_window is present
|
10 months ago |
AlpinDale
|
e702f587cf
feat: add batched RoPE kernels (#371)
|
10 months ago |
AlpinDale
|
3d6695cfbb
feat: add approximate gelu activation kernels (#370)
|
10 months ago |
AlpinDale
|
5fa15b4435
fix: double free with sliding window (#369)
|
10 months ago |