refactor: Remove speculative decoding parameters from stateful decoders
Simplify StatefulGptDecoderBatched constructor:
- Remove speculative decoding mode parameter
- Initialize with default mode=None
- Update GptSession class accordingly
Simplify setup method signatures in StatefulGptDecoder and StatefulGptDecoderBatched:
- Remove maxTokensPerStep parameter
- Initialize decoders with default maxTokensPerStep=1
- Update GptSession class accordingly
/bot run
PR_Github #290 [ run ] triggered by Bot
PR_Github #290 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #279 completed with status: 'FAILURE'
/bot run
PR_Github #320 [ run ] triggered by Bot
PR_Github #320 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #299 completed with status: 'FAILURE'
/bot run
PR_Github #396 [ run ] triggered by Bot
PR_Github #396 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #352 completed with status: 'FAILURE'
/bot run
PR_Github #421 [ run ] triggered by Bot
PR_Github #421 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #363 completed with status: 'FAILURE'
/bot run --disable-fail-fast
PR_Github #462 [ run ] triggered by Bot
PR_Github #462 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #394 completed with status: 'SUCCESS'
Looks good to me
/bot reuse-pipeline
PR_Github #583 [ reuse-pipeline ] triggered by Bot
PR_Github #583 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #462 for commit 094c3de