Grace 584e2d646f Add deepseek v3.1 (#13063) ...

* Add mla for flash attention
* Revert to using chunks

2025-11-17 18:03:21 -08:00

..

bert

chore: update models to use slice/chunk/chunksections (#12934)

2025-11-13 15:20:12 -08:00

deepseek2

Add deepseek v3.1 (#13063)

2025-11-17 18:03:21 -08:00

gemma2

s/From*Slice/From*s/ (#12255)

2025-10-28 12:08:49 -07:00

gemma3

s/From*Slice/From*s/ (#12255)

2025-10-28 12:08:49 -07:00

gemma3n

chore: update models to use slice/chunk/chunksections (#12934)

2025-11-13 15:20:12 -08:00

gptoss

chore: update models to use slice/chunk/chunksections (#12934)

2025-11-13 15:20:12 -08:00

llama

s/From*Slice/From*s/ (#12255)

2025-10-28 12:08:49 -07:00

llama4

chore: update models to use slice/chunk/chunksections (#12934)

2025-11-13 15:20:12 -08:00

mistral3

chore: update models to use slice/chunk/chunksections (#12934)

2025-11-13 15:20:12 -08:00

mllama

s/From*Slice/From*s/ (#12255)

2025-10-28 12:08:49 -07:00

qwen2

s/From*Slice/From*s/ (#12255)

2025-10-28 12:08:49 -07:00

qwen3

feat(model): add qwen3vl (#12665)

2025-10-28 17:39:47 -07:00

qwen3vl

chore: update models to use slice/chunk/chunksections (#12934)

2025-11-13 15:20:12 -08:00

qwen25vl

chore: update models to use slice/chunk/chunksections (#12934)

2025-11-13 15:20:12 -08:00

models.go

feat(model): add qwen3vl (#12665)

2025-10-28 17:39:47 -07:00