Skip to content

Actions: ggerganov/llama.cpp

Pull Request Labeler

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
4,069 workflow run results
4,069 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CUDA: Enable K-shift operation for -ctk q8_0 (limited)
Pull Request Labeler #4019: Pull request #9571 synchronize by Nekotekina
September 21, 2024 07:48 14s
September 21, 2024 07:48 14s
server: disable context shift
Pull Request Labeler #4018: Pull request #9544 synchronize by VJHack
September 21, 2024 05:35 15s
September 21, 2024 05:35 15s
llama: remove redundant loop when constructing ubatch
Pull Request Labeler #4017: Pull request #9574 opened by shankarg87
September 21, 2024 02:06 11s
September 21, 2024 02:06 11s
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG
Pull Request Labeler #4016: Pull request #9573 opened by slaren
September 21, 2024 01:39 17s
September 21, 2024 01:39 17s
CI: Provide prebuilt windows binary for hip
Pull Request Labeler #4015: Pull request #9467 synchronize by no1wudi
September 21, 2024 00:07 24s
September 21, 2024 00:07 24s
CI: Provide prebuilt windows binary for hip
Pull Request Labeler #4014: Pull request #9467 synchronize by no1wudi
September 21, 2024 00:06 16s
September 21, 2024 00:06 16s
CUDA: Enable K-shift operation for -ctk q8_0 (limited)
Pull Request Labeler #4013: Pull request #9571 synchronize by Nekotekina
September 20, 2024 21:33 15s
September 20, 2024 21:33 15s
server: disable context shift
Pull Request Labeler #4012: Pull request #9544 synchronize by VJHack
September 20, 2024 19:56 21s
September 20, 2024 19:56 21s
server: disable context shift
Pull Request Labeler #4011: Pull request #9544 synchronize by VJHack
September 20, 2024 19:54 18s
September 20, 2024 19:54 18s
CUDA: Enable K-shift operation for -ctk q8_0 (limited)
Pull Request Labeler #4010: Pull request #9571 opened by Nekotekina
September 20, 2024 19:11 20m 39s
September 20, 2024 19:11 20m 39s
quantize : improve type name parsing
Pull Request Labeler #4009: Pull request #9570 opened by slaren
September 20, 2024 18:16 33m 11s
September 20, 2024 18:16 33m 11s
sync : ggml
Pull Request Labeler #4008: Pull request #9567 synchronize by ggerganov
September 20, 2024 17:36 20s
September 20, 2024 17:36 20s
sync : ggml
Pull Request Labeler #4007: Pull request #9567 synchronize by ggerganov
September 20, 2024 17:13 17s
September 20, 2024 17:13 17s
sync : ggml
Pull Request Labeler #4006: Pull request #9567 synchronize by ggerganov
September 20, 2024 16:13 25s
September 20, 2024 16:13 25s
sync : ggml
Pull Request Labeler #4005: Pull request #9567 opened by ggerganov
September 20, 2024 16:10 17s
September 20, 2024 16:10 17s
ggml: Add run-time detection of neon, i8mm and sve
Pull Request Labeler #4004: Pull request #9331 synchronize by eddnjjn
September 20, 2024 13:57 1h 23m 30s
September 20, 2024 13:57 1h 23m 30s
baby-llama : use unnamed namespace in baby_llama_layer
Pull Request Labeler #4003: Pull request #9557 synchronize by danbev
September 20, 2024 13:50 1h 3m 40s
September 20, 2024 13:50 1h 3m 40s
server: disable context shift
Pull Request Labeler #4002: Pull request #9544 synchronize by VJHack
September 20, 2024 13:49 6m 13s
September 20, 2024 13:49 6m 13s
baby-llama : use unnamed namespace in baby_llama_layer
Pull Request Labeler #4001: Pull request #9557 synchronize by danbev
September 20, 2024 13:06 26m 13s
September 20, 2024 13:06 26m 13s
baby-llama : use unnamed namespace in baby_llama_layer
Pull Request Labeler #4000: Pull request #9557 reopened by danbev
September 20, 2024 12:57 34m 51s
September 20, 2024 12:57 34m 51s
vocab: refactor tokenizer to reduce the overhead of creating multi times tokenizer
Pull Request Labeler #3999: Pull request #9449 synchronize by kylo5aby
September 20, 2024 11:08 9m 45s
September 20, 2024 11:08 9m 45s
vocab: refactor tokenizer to reduce the overhead of creating multi times tokenizer
Pull Request Labeler #3998: Pull request #9449 synchronize by kylo5aby
September 20, 2024 10:51 19s
September 20, 2024 10:51 19s
vocab: refactor tokenizer to reduce the overhead of creating multi times tokenizer
Pull Request Labeler #3997: Pull request #9449 synchronize by kylo5aby
September 20, 2024 09:19 23m 4s
September 20, 2024 09:19 23m 4s
Update CUDA graph on scale change plus clear nodes/params
Pull Request Labeler #3996: Pull request #9550 synchronize by agray3
September 20, 2024 08:05 41m 17s
September 20, 2024 08:05 41m 17s
CUDA: fix sum.cu compilation for CUDA < 11.7
Pull Request Labeler #3995: Pull request #9562 opened by JohannesGaessler
September 20, 2024 08:02 25m 12s
September 20, 2024 08:02 25m 12s